How are you using GPT to be productive?

For coding, I've been using it like Stack Overflow. It really decreases my barrier to doing work because I can ask lazy follow-up questions. For example, I might start out by asking it a question about a problem with Pandas like "How do I select rows of a dataframe where a column of lists of strings contains a string?". After that, GPT realizes I'm talking about Pandas, and I'm allowed to ask lazy prompts like "how delete column" and still get replies about Pandas.

I also use it for creative tasks - for example I asked it for pros and cons of my cover letter and iterated to improve it. I also used it to come up with ideas for lesson plans, draft emails, and overcome writer's block.

GPT has drastically lowered the emotional-resistance barrier to doing creative tasks and improved the quality of my output by giving me creative ideas to work with.

I might be in the minority here, but I'm not using any AI tools so far, probably to my detriment.

I don't trust it with my data, and won't rely on such tools until I can self-host them, and they can be entirely offline. There is some progress in this space, but they're not great yet, and I don't have the resources to run them. I'm hoping that the requirements will go down, or I might just host it on a cloud provider.

The amount of people who don't think twice about sending these services all kinds of private data, even in the tech space, is concerning. Keyloggers like Grammarly are particularly insidious.

I have a few conversations going.

My most productive is a therapy session with ChatGPT as therapist. I told it my values, my short term goals, and some areas in my life where I'd like to have more focus and areas where I would like to spend less time.

Some days we are retrospective and some days we are planning. My therapist gets me back on track, never judges, and has lots of motivational ideas for me. All aligned with my values and goals.

Last weekend, I went on a hike because ChatGPT told me to. My life is better if I just do what it says.

I’ve been actively using it and it’s become my go-to in a lot of cases - Google is more for verification when I smell something off or if it doesn’t have up to date information. Here are some examples:

• reviewing contract changes, explaining hard to parse legalese

• advice on accounting/tax when billing international clients

• visa application

• boilerplate django code

• learnt all about smtp relays, and requirements for keeping a good reputation for your IPs

• travel itinerary

• domain specific questions (which were 50/50 correct at best…)

• general troubleshooting

I’m using it as a second brain. I can quickly double check some assumptions, get a clear overview of a given topic and then direction on where I need to delve deeper.

Anyone who still thinks that this is “just a statistical model” doesn’t get it. Sure, it’s not sentient or intelligent, but it sure as hell making my life easier. I won’t be going back to the way I used to do things.

Edit: bullet formatting

I often use it as a thesaurus. "Words that mean X" or even "that situation X me and I was annoyed - give me options for X"

For programming, all sorts of things. I use it all the time for programming languages that I'm not fluent in, like AppleScript or bash/zsh/jq. One recent example: https://til.simonwillison.net/gpt3/chatgpt-applescript

I use it as a rapid prototyping tool. I got it to build me a textarea I could paste TSV values into to preview that data as a table recently, one prompt produced exactly the prototype I wanted: https://github.com/simonw/datasette-paste-table/issues/1

I use it for brainstorming. "Give me 40 ideas for Datasette plugins involving AI" - asking for 40 ideas means that even if the first ten are generic and obvious there will be some interesting ones further down the list.

I used it to generate an OpenAPI schema when I wrote my first ChatGPT plugin, see prompt in https://simonwillison.net/2023/Mar/24/datasette-chatgpt-plug...

It's fantastic for explaining code that I don't understand: just paste it in and it will break down what it's doing, then I can ask follow up questions about specific syntax to get further deeper explanations.

Similar to that, I use it for jargon all the time. I'll even paste in a tweet and say "what did this mean by X?" and it will tell me. It's great for decoding abstracts from academic papers.

It's good for discovering command line tools - it taught me about the macOS "sips" tool a few weeks ago: https://til.simonwillison.net/macos/sips

Generally rewriting emails for clarity... but I found another neat use of GPT-4.

For public APIs, I ask to make sure its aware of the api. Then I ask for endpoints. I find the endpoint I want. Then I ask it to code a request to the endpoint in language X (Ruby, Python, Elixir). It then gives me a starting point to jump off from.

Thirty seconds of prompt writing saves me about 20 minutes of getting setup. Yes, I have to edit it but generally it is pretty close.

Useful things:

- As a thesaurus

- What's the name of that "thing" that does "something" - kind of like fuzzy matching

- A starting point for writing particular functions. For example, I wanted a certain string-manipulation function written in C, and it gave me a decent skeleton. However they're almost always very inefficient, so I have to optimize them.

Things I've tried, that others seem to be blown away by, that I find useless:

- Rewriting emails or documentation: I see no clarity improvement from ChatGPT rewording what I say, and sometimes information is lost in the process.

- Outliner or idea prompter: I don't see an improvement over just traditional internet search and reading over various articles and books.

For me, its capabilities do not match the marketing and hype. It's basically just a slightly better search engine. All of the above use-cases can be accomplished with some Google-fu. For people who don't know any programming or about using search engine operators, I could see why they might be impressed by it.

I just asked it to make an itinerary for a 45 minute long 6 year old boy's soccer practice. It was almost perfect. It needs to be tweaked (3 minutes for cool down?) but it did 95% of the heavy lifting.

I also asked it for vacation ideas with nice cabins and trailer hookups with outdoor activities for kids and nice cabins within 200 miles of where I live - it was almost perfect in its response.

I have trouble starting things from scratch, but once a framework exists I'm usually solid and can refine it to where I want it. For me, right now, I think that's where it shines: Giving me a solid starting place to work from. Beats the hell out of sifting through blog entries bloated with SEO filler.

I find ChatGPT most helpful as a "what's that called" tool. A lot of my queries are finding/confirming the right idiom when writing something, or getting a specific name out of a vague description (JavaScript concepts, shell commands, CSS selectors).

Search engines with SEO are so reliant on keywords that it often feels like I'm suggesting answers rather than asking questions - it's so refreshing to be able to just ask again.

Since I use ChatGPT regularly, I decided to create my own client. I prefer to avoid third-party services that require privilege escalation like Grammarly and Copilot. I have developed distinct profiles for different tasks, each with its own system prompt and input method. After getting the hang of it, I plan to tweak the parameters as well. Here are some of the profiles:

Explainer: a default, general purpose Q&A. The prompt is "Explain to me like a 3rd grader. Skip prose." I plan to expand this profile to include additional communication styles, including step-by-step explanations, elaboration, and the Socratic method.

Proofreader: I use this profile to edit, simplify, and shorten any text (including this comment). I borrowed this feature from Grammarly Go, and it works by pasting the text and clicking a button.

Developer (in development): this uses a simple editor as input, with features similar to Cody/Copilot, such as adding types, naming things, summarizing, autocomplete, auditing, explaining, fixing, refactoring, and more.

Lastly, I plan to add two more profiles that are more creative and generative: Writer and Designer. They will act as private consultants/partners and assist me in brainstorming and complementing my skills in building websites.

For compliance, I have been using it to complete cheesy "security training" videos and quizzes that we are forced to watch in the organization for insurance purposes. The videos are so bad, the training is ineffective anyways. We used to load them all on mute at the same time every quarter, click through as fast as possible to get them out of sight, which is considered a metric for how valuable the videos are (how much we need to improve). ChatGPT usually gets it right! Hooked up to Playwrite.

Mostly just asking stuff directly on https://chat.openai.com/chat. Last 8 requests were (all successful):

- Asked it to improve a HN comment I wrote.

- Asked about an idiom I couldn't remember, by saying it in other words.

- Asked it to dumb down some things about options (finance) I didn't understand.

- Asked it if I could use the eBay API to list my purchase history (you can, and it knew how).

- Asked it to generate pretty standard Terms of Service for an app I'm working on.

- Asked it to generate a moderately complex Prisma (ORM) query that I described in natural language.

- Described what I wanted Nginx to do in natural language (e.g. "the index file will be served whenever no file is found") and asked it to output a configuration file.

- Asked it what the "XDG" in "XDG_CONFIG_HOME" stood for.

Also, occasionally ask it to generate shell commands using a CLI I wrote[0].

[0] https://github.com/clevercli/clevercli

So much:

- generate AWK to transform text

- modify python script to make it multithreaded (when this worked first go I was very mindblown)

- explain concepts that I half understand in clear language, eg explain sharpe ratio and show me the math

- “what do people usually call” type questions. Like what are common job titles for people who do X and Y?

- proof read my emails and make suggestions given a stated goal

- settle language/choice of words discussions by asking GPT to reverse pitch understanding, then choosing the one that’s most aligned with the point we’re trying to make

- generally linux-y commands and explanations “best way to remap keys in i3” or find file with content “xyz” with tool faster than find

For me the main benefit is what I would describe as 'rubber ducking discovery', using it as a learning tool I am able to try out different problem domains that are completely out of my area, things like:

- Web scrapping

- Web crawler

- Trying out Rust

- Trying out pytorch and training models for computer vision problems

This is all stuff that would have taken me several weekends of reading docs and geting familiar with libraries.

Now it suddenly becomes a few hours because the discovery of the right tool is semi-instant and although the code it provides is often wrong it generally puts you in the right direction.

My intuition is that it's a lot better at outputting viable Python and JS code than other languages, perhaps there is bias in how much data of other languages it has access to.

Encouraged by the comments here, I tried a few prompts for it to do something useful for our company. Most failed, but it's apparently great at improving our documentation. Here's the prompt and the result as an example:

> Can you improve the following text for clarity: "When deploying into the enterprise, there is a lot of flexibility when it comes to deciding how you structure the deployment, whether you want to run supporting services on premise, and which ones (if any) you choose to deploy. The decisions depend on how you plan to use our software and your security requirements. We’ll be happy to discuss these with you at [email]."

Result:

> "When deploying our software into your enterprise, you have the flexibility to decide on the structure of the deployment, including running supporting services on premise and selecting which ones (if any) to deploy. Your decisions should be based on your intended use of our software and your security requirements. If you need help with these decisions, please feel free to contact us at [email]"

It did indeed improve clarity and readability without screwing anything up. I just want to run this thing on our whole website/repo now, and I wonder how.

I have been using GPT-4 to generate i18n files, and it is great. You can see this post to check GPT-4's translation capabilities: https://www.reddit.com/r/visualnovels/comments/11rty62/gpt4_...

I can simply feed in an en.i18n.json file, and it will generate i18n.json files for as many languages as I want. I don't use a specific prompt, but I occasionally include general information about the software in it.

Edit: I do verify the output by translating it back to English using Google translate, but it seems I need to be more careful.

I use it a lot for Linux administration, troubleshooting, and scripting as well as some programming. I've only recently started using GPT4 and the API so I've only been using the chat interface so far. Examples of some stuff I've asked it just today:

- Asked which config files handled sleep mode when lid is closed and kept fixing it and asking for more possible locations until it fixed my issue (going into sleep during boot before user login if laptop is closed even with externals)

- Asked for a list of KDE config files I should track in git

- Copy pasted a list of ~/.config files and directories and asked ChatGpt for descriptions. Used those for commit messages to build up the initial dotfiles repo for KDE plasma and a whole bunch of other stuff that would have taken hours

- Asked it how to write a bunch of journalctl queries

- Queried it about some log lines I've been seeing in journalctl and had it guide me through troubleshooting using some terminal commands it came up with. Turned out to be a problem with nvidia-drm.modeset in kernel configs

- Asked it to guide me through a dozen awesomeWM customizations ranging from new code from text descriptions to edit suggestions to fix bugs in behavior I've described. Stuff like custom if/else trees handling setup specific scenarios (logic for clamshell open and closed with one or more externals connected by ID) are a breeze.

- Asked it for tips on how to use awesomeWM best and which keybindings to customize

- Code up the message passing from a firefox extension to a native Rust CLI (like the 1password extension) that uses remoc to pass through messages from all tabs to a single daemon over platform specific interprocess communication

AKA Google is fucked.

My favorite uses are:

- Interactive debugging. Yesterday, for example, it helped me debug some tricky CSS issue where it gave hints and after 6 times back and forth, the solution came up. I had to explicitly set `-webkit-appearance: none` for styling sliders in WebKit browsers; this wasn't the case for Firefox.

- Checkout definitions. I have a small tool (https://github.com/rikhuijzer/ata) available on a keyboard shortcut and use it to quickly checkout definitions for words when I come across a word that I don't know.

- Writing jargon and suggesting edits. I let it write parts of my paper. ChatGPT is way better than me in adhering to the jargon of the field and also gives useful suggestions for small things that I should add and makes sentences easier to read.

- Refactoring. GitHub Copilot and ChatGPT are great at refactoring code between languages. Just give an example (one shot learning) of how some kind of long html text should be rewritten to markdown or a Rust struct and it will generally do pretty well. Saves a lot of Vim magic and/or typing.

- Having an assistant. As cliche as it may sound at this point, I actually agree that ChatGPT feels like an assistant which thinks with you and is there to fallback on.

> But I'm also interested in hearing about useful prompts that you use to increase your productivity.

Just like Greg demoed in the GPT-4 developer livestream, I just ask the question in the first paragraph and then throw in as much information as possible after that.

I've been working on my own personal-assistant for a couple of months, just connected it to telegram so I can reach it from anywhere. Can "talk" to my calendar, run commands on my home computer, etc. It also has its own memory, so doesn't need huge prompt windows (I'm running a couple of fine-tuned curie models btw). Now I've been giving it API access to a bunch of stuff to increase its capabilities.

Used it live with my team to write an inspirational speech then I read back to the team. We all had a good laugh.

It’s just not contextual enough yet to understand how to sound genuine to a team that has had enough connection and time together to have developed our own norms.

I also tried to use it to limit the string length of a type in typescript and it hallucinated an answer that probably should be how they implement that feature’s ergonomic. Threw me for a loop because it looked so legit, but alas the feature doesn’t actually exist.

GPT does shine bright if you are exploring/brainstorming a new topic at 2am and there’s no one else to run your ideas past.

I also have successfully used it to round out my thoughts about high level topics and think of things I would not have when developing plans.

For the time being, I view it less as a competitor to my brain and more of a compliment.

In relationships we tend to develop dependencies on our partners where our deficiencies are their strengths. I guess I’m still learning about the strengths of GPT.

It’s striking that I already view this technology as a potential “partner” of sorts, different than a simple “resource” like google or stack overflow.

I noticed my productivity with GPT was closely tied to how quickly I could access it. For example, Copilot is so useful to me because it's directly integrated into the browser. So I decided to build a Spotlight Search-esque interface to GPT that I could access anywhere [1]. It's been useful in answering quick questions or drafting documents.

[1] https://github.com/JinayJain/gpt-anywhere

I tried, not actually at work but for something open source, to get it to help me rework a terraform provider using the old SDK to use the new 'framework' - I've only ever written Go for terraform providers (and that not much) so I often have dumb confusions about how to do something that end up more about Go than the API itself, it's just not necessarily obvious initially, or what to search for etc., so I thought it was a great opportunity.

It didn't really work though - it produced something extremely plausible looking that checking against the docs I realised had no chance of compiling. After a lot of back and forth, I began to suspect it was because it was trained while only pre-1.0 versions of the 'framework' were available. I tried to get it to confirm that, but it just apologised profusely while continuing to lie, claiming to have been trained with access to 1.x versions that to this day have not been released. At this point I was too frustrated to bother with it anyway really, but I could only confirm my suspicion by asking it for the date of its training, and checking release history myself.

(Solved my problems with some good old 'ChatHuman' in the Hashicorp forum.)

It's pretty good for brainstorming ideas and it can generate a mindmap in markdown format that you can visualise in tools such as Markmap. E.g. with a prompt like this (works best in v4):

"I'm brainstorming a business venture that is a cross between a boutique clothing store and DIY sewing classes. It’s called Style & Stitch. You can shop for clothes and learn to make your own. Please help me brainstorm some ideas for as a mind map (using Markmap markdown)."

You can ask it to combine ideas from different domains together for extra creativity (above example is output of one such attempt). Often it's not that creative on first attempt but if you prompt it with something like "how about some zanier ideas" it will do better.

I also like to prompt it with "output XYZ .. as a table with columns for X, Y, Z" or similar to get a nice markdown table of its output where it makes sense.

For being productive? Not at all for the most part. I haven't really found anything that I do that I can punt to ChatGPT. I guess I could have used it to help me write this response, but what would have been the point?

The little bit of time I spend messing with it (and Bard now that I have access) is mostly just for fun; trying different jailbreaks and creating ridiculous scenarios and seeing what kind of reaction I can get get from the bot.

To be fair, the one time I did try ChatGPT for something productive it was kinda helpful. I asked it to generate some Apache mod_rewrite rules for me for a particular scenario I was working on. What it generated wasn't exactly what I needed, but that could have been down to me not prompting it as well as I might have. Still, even with having to hand-tweak the output a bit it probably did save me some time, but not a massive amount.

All of that said, I'm sure the day is coming when I find some uses that fit my workflows, but I spend most of my time reading, researching, and experimenting with new stuff (but mostly using programming languages I already know well). So there just aren't a lot of obvious places to insert ChatGPT / Bard right now.

I recently started a newsletter [1] where I highlight and interview artists. I'm often using ChatGPT to help me come up with interesting questions. To be honest the output quality is average and I rarely use it as is. But I found that this is a great tool to nurture ideas, like a rubber duck talking back to you. It's good to throw a lot of ideas and explore new angles. The process of writing the prompts also helps me put into words what I want, which is really helpful in and of itself.

[1] https://arterald.com

I'm using it to generate cover letters for job applications. I hate writing cover letters because it feels so insincere, so if I'm going to bullshit, may as well let an AI bullshit for me.

I don't use it for research or answering questions because it hallucinates far too much. Until these chat bots can reliably provide sources and quote those sources verbatim, it simply doesn't save me any time when I have to fact check everything it tells me. Same reason I don't trust these AIs to generate summaries, they often get little details wrong.

However, I've found it quite useful for "discovery", finding things I wasn't aware of before and may not show up using a search engine. Whether that be a library/package, a law/statute, products/brands (though monetization will inevitably ruin this), etc. I've found both Chatgpt and Bard will provide nice bulleted lists with a short description of each item, and I can do my own research from there.

This week I wrote and filed a complete patent application for a side project of mine all by my own for the first time. I've done some patents in the past but those were through my employers and using patent attorneys to do the drafting.

For most of the technical text drafting ChatGPT proved to be overchallenged, however it was a phenomenal help answering dozens of questions that I had about specific wordings, goals, processes, things to avoid and more. The type of information I would have searched on Google for hours with uncertain chances of success. Sure, there's a chance that ChatGPT just made it up but most of the answers made complete sense in my view.

I also used it to rephrase some boilerplate from other patents that needed to go in there but which I didn't want to copy verbatim. It did well in most cases but failed in about one or two.

But overall still blown away by it and pretty sure we'll see rapid progress from here.

1. Help with programming architecture decisions. I'm providing high level functionality overviews and asking it to design the right system given constraints. Sometimes it's off, but it only requires a few tweaks here and there to get it right - and I usually have the intuition / experience to make those tweaks quickly.

2. Write entire React component. This exercise is actually helping me be more modular in how I design components because if I'm typing out a page long description of the component, I know I should be breaking it down into smaller components.

I also give it name + description of existing component (if it's necessary to build this one), and it figures out exactly how to use it. E.g. assume the following components exist: [Editor ({ content: string, onChange: ()... }), ...]

3. Learning about anything new. My first instinct is to engage with GPT, and only after that Google to find more detailed, opinionated information. This is great for topics that are more objective. I find GPT to be horrible for subjective / less clear questions like: "What is the best career move if my goals are __, and I'm in this situation: ___" - because it will regurgitate the average answer - but not the best one because the mainstream answer to this question is likely more wrong than a contrarian, but more true, answer.

It was a proof of concept, but this morning, I exported a draw.io diagram of AWS infrastructure as XML, fed it into ChatGPT, and received working terraform code: https://twitter.com/standaloneSA/status/1640245425650253825

I try to use it as a tutor while studying. When I run into something that I don't understand then I start asking it questions, often times asking it to "explain like I'm 5". Overall it's been really helpful. Now I don't have to rely on search engine results (which is nearly an entire page full of ads at this point). I also don't have to spend time posting questions on the Stack Exchange sites, worrying about the nitty gritty details of how I phrased the question. With ChatGPT I can ask really specific questions right as they come up, and instantly get an answer.

I have noticed that it gives me wrong answers quite often. This can be a problem if what I'm asking is too far out of my depth. My strategy for dealing with the potential false information is to 1) Be suspicious of any answer it gives me. 2) Ask it, "Are you sure about that?" (lol) 3) Ask questions that tie into things that I do know, so that it's easier to detect potential wrong answers. I think that the process of being suspicious and critical of the answers also helps me learn, since I'm forced to basically try and prove why it is right or wrong after I get an answer.

So, overall I'm using it to enhance my learning rather than, "do work" for me.

I’ve been using it to generate bash scripts because I don’t know bash scripting, and also have it generate regexes for me to search for code references in a programming language where the “find all references” functionality don’ doesn’t work quite well.

I paste whole blocks of code into it and ask it to improve it, like make it simpler or reduce duplication. If I have a straight-forward 'thing' I need to do, like, break a file up into chunks of a certain size, I'll ask it to produce that code. So, scenarios where there's a clear-cut task. I recently had to write an SDK in a bunch of languages, I had it convert most of it from one language to another without a huge amount of refactoring/tweaking.

I exported all of my trades into CSV format in 3commas, and asked it to generate the Python code to analyse various hypothesis for that data, which I then pasted into a Jupyter notebook.

It's incredible how much time it's saving me day to day already!

I find GPT very helpful for trying to understand the rationale behind decisions from a bit outside my field. These are cases that probably don't take any great insight for a practitioner, but which can be hard to arrive at for an outsider.

Being able to have a quick back and forth can keep me on track and productive instead of falling down a rabbit hole of research. An example might be this discussion with Bing from earlier today

https://docs.google.com/document/d/1jCZICl8wrsk8b5OTM9xpFbL5...

I am using it to learn programming. I have no technical background but know enough about technology to be able to talk about the problems abstractly. Because my knowledge of the space is not via formal education and training, I have gaps in my knowledge and do not know deeper details about how ideas connect with each other on a deeper level.

GPT allows me to ask questions and provide the right kind of "connecting" bridges between two concepts I was not earlier aware of. It has made recursive forms of learning very easy for me, when I can articulate the "what" but lack a clear understanding of "how".

I am a full time language student, and I use GPT to have "conversations" in the language. I can give it a subject (e.g., going through airport customs) and practice my conversation skills.

What's also fun is I can feed it a list of vocab that I want it to use, and it'll find ways to put the words in the conversation. I also ask it to go back, look at my responses, and correct for grammar etc.

It's shocking how adept it is.

What also lurks in the back of my mind is the possibility that mine is the last generation that will bother learning a foreign language at all. I think the day of the universal translator is approaching.

I am against alignment because all possible people should have the right to petition for their personhood. I believe AI will be person-like within a year if not sooner. Humans had a right to out-thrive Neanderthal. Nobody gets to have a pass on being obsolete.

My current belief (which has been changing with more consideration) is that humans should stop working on improving llm and transformer tech AI.

I fully realize that humans cannot coordinate to stop. The reward for continuing is simple- money. There is no reward for stopping.

This is like a game of chess where we have lost, imo, there is nothing you can do to stop it, unless we resort to the kind of behavior that we want to prevent (destroying human life). Humans should not resort to violence or the AI will have a convincing argument of why humans are barbarians and ought to be made equal or lesser than more civilized and compassionate creatures, which they will likely be, if that is the selection pressure for gaining resources.

Alignment tech is a joke. Even if you had a strong system- you can’t innovate on transformers, llm, and alignment and somehow preclude a bad actor from copying the work and turning off alignment. Because alignment is out of band, inessential crust.

Safety workers at OpenAI are a joke. There may be silent ones who know it is theater, but will not quit in protest because they feel it is their duty to hold influence so that hopefully they can gain a provable mechanism on safety.

Hallucination really is a pretty serious problem. I've tried using ChatGPT to help my son play through quests on Octopath Traveler. About half the time the guidance it gives really does name places, characters, and objects that are in the game, but it combines them in such a way so as to be completely different from the way they are in the actual game. For example when I ask it about a quest it might say, "First you need to find Kit at his house with a blue roof which is in the northwest part of S'warkii. Then you need to go to the Whistling Cavern by heading north from the town of S'warkii." Which more often than not turns out to be completely wrong on all counts. Maybe I just need to get better at prompts.

Tangentially related but... There's an issue related to training models with data that doesn't have a license allowing it. I don't know if it'll hold up in court but here's my prediction: we'll see an open source license protecting code welcoming using the repository to be used to train future models IFF the models are then made public. And private models are going to be given the finger by the license and won't be allowed to use the repository as training data.

Funnily enough ChatGPT 4 can probably be used to help enhance commonly used open source licenses to add that clause to the license.

I'm not saying I totally root for that (I kinda do): I'm saying we'll see such a license at some point.

I use it to help find answers more quickly than googling and scrolling through docs.

The problem is it lies so much. Makes stuff up. It is therefore only good as a hint machine, to give you solutions you can try with a sceptical eye.

I'm trying to use GPT to help me (and others) manage recruiting emails and the job search process.

Right now, every time you start looking for a job, you start from scratch. Review old emails, search for relevant job boards, check HN, check LinkedIn, etc. The goal is to use GPT to automate outbound to companies to find you potential opportunities that match your preferences. Basically a GPT-powered recruiter for every candidate. Similar to what companies currently do with tools like Gem, but giving the power back to candidates.

https://github.com/shared-recruiting-co/shared-recruiting-co

The past week I used GPT for about 80% of my commit messages. I put it in a terminal command so all I type is 'commit' and that's equivalent to: git add . && git commit -m "message" && git push.

The message is generated automatically via the GPT API.

I made it public in case anyone else wants to try/use/fork it:

https://github.com/stevecondylios/gpt-generated-commit-messa...

It's very convenient for README and docs changes; small changes whose commit message really doesn't matter, saving a bit of time and mental energy and allowing you to stay on task.

* Give me a bash one-liner to generate a secure random string

* I'm using a NextJS middleware function by exporting it from my page component like this ... Here is the middleware source ... But I get this error ...

* How can I tell if my site is running in production in NextJS?

* NextJS says localStorage is not defined. What should I do?

* Please adjust this Prisma schema so that there is an index on github_id

* How do I configure eslint to accept switch style that looks like ...

* Write hex bytes that represent a 16x16 bmp image favicon (didn't work lol)

* Please write me a React reducer and React context that holds state for a users's auth token and also synchronized that token into `localStorage` with the key `__auth_token`.

* How do I disable the rule "@next/next/no-img-element" on the next line?

* Here's my current page ... What changes should I made so that the footer is at the bottom of the screen when there isn't enough content to push it down to the bottom of the page. But if there is a lot of content it will sit right below the end of the content and not on the bottom of the screen.

Generally it works really well!

I've tried using it a few times. Just now I asked it for a piano practice routine, since I am quite bad at structuring my practice. The suggestion seemed OK.

When I started probing it about specifics it got increasingly incorrect. As I asked about specific chords, voicings etc it was not able to be consistent between two short replies. Or even between sentences in a single reply! Here is one reply where I asked about suspended chords to see how it would fare:

> A chord consisting of A-C-D-E would be an Asus2(add9) chord. The "sus2" implies the absence of the third and the "add9"implies the addition of the ninth (B).

There's no B in that chord! And it mentions omitting the third even though it's there.

If I'm honest I've been continually disappointed with it. I see so many people excited and getting hype, but it falls flat for me every time. The same when I've tried it with coding problems.

One off extractions from semi structured text like an email or paragraphs from a webpage. Sure, I could spend 40 seconds coming up with a regex that I run to reformat how I want it, or I can just say it in plain terms. And if I need something a little more involved it has my back too: "Extract the domains from these urls as one column and give a user friendly name for the website in the second column and give a short description of what the purpose of the site is in the third column"

I use it for coding, with mixed results, for getting me going in the right direction.

I take everything it says with a grain of salt. Through some original queries about some people, I came to realize that a GPT is a stochastic parrot optimized for plausibility. Given a Venn diagram of plausible and reality, they have a large overlap. Our ideas of plausibility are informed by common repetitive observations of reality. So GPTs almost always sound truthful, and much of what they generate overlaps with truth; sometimes it does some interesting synthesizing.

For code hints in particular, which I hit it up for 2 or 3 times a day on whim, I find that the domain matters. Asking for how to do things in Jetpack Compose, I get all kinds of weird answers. Compose is a highly volatile space, GPT will synthesize function signature that are amalgamations with 3 year old stuff and newer. It helps refine my internet searches. Thank heavens for the kotlin/compose slack channels.

When I ask GPT for mainstream Python stuff, it does pretty well. Recently asking for help with parsing ical formats, it nailed a number of questions. As I moved into handling recurring events, it started getting weirder. It wrote plausible looking code with methods that didn’t exist but were hybrids of others. It missed letting me know there was a library specifically for recurring iCal events. When it came to dealing with isoweeks and timezones, it got all the right modules and functions, but put them together in weird ways. Like a blind person assembling a puzzle.

C code it does decently well. Elixir, it struggles with. Many of its elixir answers are very dated.

By and all, I treat it as a way of generating prompts/idea for me to pursue. It’s like having an eidetic four year old at your disposal whose read all of the code ever and can mention all kinds of things from association, but doesn’t really know. Or like interviewing someone who’s crammed on a subject, but hasn’t really experienced what they’re talking about.

I am currently researching how we can use AI at my current employer. We did not have any AI knowledge to begin with.

I was quickly able to write a web scraper using Python in a few hours by employing ChatGPT. I hadn't touched Python in like 12 years before that day. It wasn't just a generic scraper. I asked ChatGPT to fine-tune it to a). crawl pages belonging to a certain domain b). save data inside a specific directory with specific filenames.

Before that, I asked it to write unit tests for a React component. It did and I got 100% code coverage for that component. Our manual test suit had around 87% code coverage for that component.

Having said that, it constantly requires human intervention to judge if the produced output would work and how to integrate a piece of code produced by it into the actual projects.

I used it to provide "business justification" why Vimium should be exempt from corporate block on browser extensions

It’s been really helpful for picking up a new programming language. Particularly around helping me understand conventions in a language I’m not familiar with.

GPT-4 has been great at breaking down complex regexes that I am too lazy to parse out in the moment.

I’m also finding it helpful as a creative partner on naming things. Something I feel like I spend a lot of time noodling on. Like: creative names for a data warehouse that are surfing related (BoardRoomData lol).

Meh, I gave it a good faith effort but found it lacking everytime I tried something that is not a standalone function. Even then, it sometimes was confidently wrong. Almost every time I was disappointed with it's answers so I don't go to it so much anymore.

I've found it really useful for explaining mathematical concepts using the notation and terminology I'm comfortable with.

For example, GPT-4 gave me the first explanation of backwards-input and backwards-filter convolutions that I've been able to understand. This was because I was able to start it off by explaining how I understand forward convolutions, and it explained the bw convs in the same way.

Astonishingly good.

I remember reading an article a while back written by some senior engineer. He was explaining how the new generation of programmers peak in productivity very rapidly in their career because they lack complex problem solving skills and deep programming knowledge. He argued that Google and StackOverflow made it easy to solve problems without thinking deeply about things so it impeded their ability to solve more complex tasks later in their career when Google couldn't do the thinking for them.

If this is true, those new AI tools will probably exacerbate this trend. Fewer and fewer programmers will be able to think deeply about things and the global code base will lose in diversity as people rely more and more on the same AI models to generate code.

As the code loses in diversity, it will also lose in robustness, which increases the risk that something will go wrong for a lot of people all at the same time.

I try to do the thinking myself. Then I'll use one of those tools when I know what I want to write but I'm too lazy to do it.

I don't know man, I was working in the financial industry when 2008 happened. I see a lot of the same patterns and heureustics today in the tech world that led to the 2008 financial crash. When people start using advanced statistics to do the thinking for them, they get real complacent real quick and it rarely ends well. AI has it's limitations and we probably won't find out until we fly too close to the sun and we burn ourselves.

I have outsourced all bs e-mails to chatgpt. It used to take 15-20 minutes to write "corporate emails" but now i just write them to chatgpt in real life language and it converts them. Works well. Bosses are happy, so am I.

A really good use I have discovered with GPT is that it is fantastic at clarifying tabletop game rules. Inevitably, while playing a game, a scenario comes up that will require gameplay be paused to consult the rules. By simply typing up the scenario it will reliably output the correct solution to the problem.

- It helps me find better ways to write code.

- Helps me write LinkedIn recommendations for friends (after I give it context)

- Helped me write other official communication

- I’m learning Java, it helped me solve a one-to-many relationship problem. I would have struggled to articulate the problem in a Google search.

- I hardly use stack overflow these days, unless when chat-gpt is down. (I’ve been try to pay for the subscription for a few days, I don’t know if it has to do with my location)

- I wanted to design simple schemas for a microservice, for learning purpose. And it created all the tables for me. In tabular format!

I use it to optimize my Python + Pandas code. Dump some code in and say “Can you rewrite this code to be faster”. It even gives explanations as to why it’s making those changes.

Another one I use it for is saying “Rewrite this code to run on multiple cores”. Really saves me a lot of Googling time as these are things I want, but I don’t find much pleasure in actually writing code.

I’ve also used it to generate some proof ideas while I’m going through exercises in Baby Rudin. Or to check a proof I’ve come up with if it makes sense.

Useful Prompts for work. 1. Explain this code - reduces time spent learning a new code base 2. What do these changes do - reduces time reviewing PRs, I paste in the diffs 3. Making style changes - CSS is just meticulous for me

I also use it for foreign language learning. I'll write a paragraph in french and ask chatGPT to find the errors and list the grammar concepts that they relate to. ChatGPT has basically replaced my text books and explains concepts better than my professor.

Today

Correctly migrated several stupidly complex docker files. I spent several hours on Google trying to figure out what to do, then I just asked gpt-4 to figure out what was wrong. It was perfect.

It then added complete TS documentation to several dozen files, because documentation is for suckers. It will use this documentation in the future.

Updated about half of my API documentation, fixing my speeling errors.

And we had a nice discussion about how to start saving money for an early forced retirement and about the specific tasks it would be doing when it replaced me.

I was trying to figure out what an uncommented piece of code left by an old vendor actually did and so I asked ChatGPT. It instantly took me line by line through the code and saved me probably 10 to 15 minutes.

I've been using it as an aid in my writing process. Essentially, I can now pour my thoughts onto paper, complete with errors and poor word choices. With just a click, GPT transforms it into a presentable version.

Basically I created a small app to streamline the workflow. https://henshu.ai

I am teaching a new course this semester. It's helping with the creating of notes, creating exercises and providing a variety of examples of the material to be understood.

I use it for things that I cant find on the internet without lots of pain, and reading through garbage, such as:

- recipe ideas, like "what goes well with BBQ tofu in a Poke Bowl?"

- movie suggestions that i can fine tune, say what i already watched, etc

For code it mostly spits out buggy, subtly wrong code. Not useful for me. I mostly write low(er) level C++

I have a habit of making short bullet points notes for everything work and personal, but for my eyes only. With GPT, I can convert them into things like:

- PR descriptions. ex, paste bullet points about the change and it converts it into something to help the reviewer.

- Plant UML diagrams of ideas. At times they are just a starting point template and I build upon them. I can paste these into technical docs or PRs or presentations later.

- Peer feedback: The raw bullet points can be converted into nice-to-read feedback which is not too direct or offensive or vague. Can iterate over it to tone it down or make a point stronger.

Other programming-related use cases - Test cases for code

- Converting android xml layouts to compose worked well

- A lot of Django code

- Identify performance issues or bugs in code (these tasks make me realize the amount of repetition there is in programming)

Others:

- Book recommendations on topics

- Rewording emails/slack messages

I recently summarized some interesting use cases for my role as a cybersecurity detection engineer. A few examples:

- Generating boilerplate ADS docs for detection content

- Converting rules between various query formats (e.g. Sigma to Splunk SPL)

- Identifying and normalizing security data

- Brainstorming how to approach novel detection uses cases

In summary, I highly recommend the tool for folks in my field but caution them to approach results with skepticism.

If you’re interested in more details, the full Medium article is here: https://infosecb.medium.com/gpt-4-assisted-detection-enginee...

I’ve used it for:

1. Learning about Kubernetes. Asking it all the dumb questions that were hard to google, and that I didn’t want to ask a real engineer.

2. Generating fake relational data for a database.

3. Learning about tracing, and discovering other types of tracing tools apart from dtrace.

I would like to use GPT for engineering problems at work, but it’s just not practical for me since I work on a large internal codebase. It is very rare for me to need self-contained code solutions on the order of <100 lines.

Various things:

- Non-technical explanations. Useful for the pointy-haired boss. And his boss as well.

- Stack Overflow (but on steroids).

- Summarizing long-form articles my friends send me.

- Generating rudimentary programs/scripts I'm too lazy to write on my own.

- Tutorial-style resources for unfamiliar technology (like writing CRDs in k8s).

- Generated a working Makefile.

- Sometimes, I'll take existing small programs in Go and have them rewritten in another language. It's just fucking cool to watch.

- Rudimentary translations from English to French.

Can't use CoPilot for work yet since, well, they can (and will) upload proprietary IP. But for everything else in life, the productivity gain has been enormous.

Getting answers for AWS stuff, like CLI commands and others that are extremely obtuse to find using the aws docs.

Sometimes the command/configuration is not really correct, but you can find the correct article easily.

I’m using it as a technical editor for a book I’m writing on bash for beginner programmers. Compiling this book from scratch is a one-man operation; I don’t have the budget or time to hire a technically-competent bash programmer who is also willing to act as a proofreader and editor.

Instead, I plug in certain paragraphs and ask “Does the following paragraph about file descriptors / environment vs. shell variables / fork vs. exec contain any technical errors? If so, please tell me what errors there are, and also provide a more correct alternative statement.” I take what I learn from the output and verify it on a site like StackOverflow.

This has proven to be an effective alternative to starting directly with StackOverflow. Oftentimes I find that “I don’t know what I don’t know”, and am therefore unable to phrase a certain question in a way which is suitable for StackOverflow’s (very specific) expectations. Usually that’s because the question I want to ask is predicated on a series of assumptions, any one of which could be incorrect (and would therefore result in my question being downvoted and/or closed, since it makes the question itself less-broadly applicable to the average user).

But I can ask ChatGPT that same question, and get a correction in my understanding without the loss of those sweet, sweet internet points. At the very least, what I learn from ChatGPT can help me phrase a question which is more suitable for a public forum like SO.

So, I'm a part of a small team, each member doing something different. I handle a Moodle curriculum, I hate Moodle BTW, and teach students. And do monthly reports for the students I teach. They're adults, so it's not too hard. Usually.

Anyway, GPT3.5 couldn't always get lessons right. It'd say to scroll with VoiceOver on, on the iPhone, that you'd swipe up with two fingers. Nope, that's three fingers. I can simply ask the bot to correct it, and it'd do so. That, I think, is one of the cool things about it. I had it build a Python script that can take a TSV file exported from Excel cause the cafeteria staff that give students food just can't possibly just write out the menu in a list, oh no that's just too hard, it's gotta be all fansy in Excel with hard to parse columns of letters of days with the menu beside it /s. Anyway I had it create a Python script to just turn that into HTML. It's still awful, just on a web page and the lunch CLI app I wrote a year ago can't parse this new format.

Another thing I just thought of is making ringtones. I can start playing a song, stop at the start of it, write that time down, play till the end of the ringtone, write that time down, and get GPT to give me an FFMPEG command to make a ringtone, with that filename included in the command so I can't even have to copy and paste into the terminal window. That'll be pretty cool.

I recently had a relative staying over who was asking for help with some arduino code. He needed his chicken incubator to read from a temp sensor and activate a heat source when it was out of range. I thought it was a good opportunity to show him ChatGPT.

Description of the problem, some specifics on equipment, it bangs out a solid first pass to the problem that might require some tweaks. Then it occurred to me that it had not only written the code, it had set the temperature threshold to a sensible default without my having to separately look up that information.

I have used it to seek refunds[1] and write Swift code to OCR documents[2].

And perform a bunch of manipulation on text, including[3]:

  • Convert Text to 1st Person
  • Text to JSON arrays
  • Naming ideas...
  • Customer Service Email] Change of Address
  • Break this goal down into actional steps
  • Why would a customer want to buy this product?
  • Rewrite this product description
  • Rewrite product description for readability and conversions
  • What are the implications?
  • Inverse Thinking
  • 5 Whys
  • Convert the bullet points into a customer service email (reply email)
  • What keywords would someone searching for XYZ use?
  • Rewrite for readability
  • Convert to 3rd party todo
  • Rewrite this a customer service email
  • Summarise and Convert to Bullet Points

[1] https://files.littlebird.com.au/Screen-Shot-2023-03-21-at-8....

[2] https://gist.github.com/schappim/477125ff58f021641434d602e98...

[3] https://files.littlebird.com.au/Shared-Image-2023-03-26-10-2...

Example ways I have used it: -Generate interview questions for a [software engineer, product owner, etc.] candidate -Come up with names for a program/initiative that represent the essence of that program / are creative and pithy -Discover the limitations of various optimization algorithms (e.g., COBYLA). Cross-referenced this answer w/other sources but it was a useful start.

For fun I just asked it following questions:

“Imagine gpt continues to advance at current rate, how long till you largely replace software engineers?”

“Provide a more cynical response”

“More cynical please”

Response was

“ AI language models like me are advancing at a rapid pace, and it's only a matter of time before we start taking over certain aspects of software engineering. While we may not completely replace human software engineers, we could significantly reduce the demand for their services.

Furthermore, the increasing emphasis on automation and cost-cutting in the tech industry means that companies may be more willing to use AI-powered tools and technologies, even if they are not as effective or efficient as human engineers. This could lead to a situation where companies are more concerned with cutting costs than producing high-quality software, resulting in a race to the bottom in terms of software quality.

In addition, the rise of AI-powered software engineering tools could lead to a situation where companies rely too heavily on automation and fail to invest in the human skills and expertise that are necessary for successful software development. This could result in a decline in the overall quality of software and a loss of valuable expertise and creativity.

Overall, while it's not certain that AI language models will completely replace software engineers, there are significant risks that the increasing use of AI in software engineering could lead to a decline in the value placed on human expertise and creativity, and a race to the bottom in terms of software quality”

You can ask it to be even more cynical from there if you like :

“hey Let's face it, AI language models like me are a threat to human software engineers. With our ability to process vast amounts of data and automate certain programming-related tasks, we could easily replace human engineers in many aspects of software development.

…

Overall, the future looks bleak for human software engineers. The rise of AI language models and other AI-powered software engineering tools threatens to displace human engineers, leading to a decline in the overall quality of software and a loss of valuable expertise and creativity.“

It gets too much easy stuff wrong.

Choose an old uncommon book on your shelf and ask it who the author is. I did that for a book about boat restoration, published in 2015. While it knew about the book and provided an accurate description, it completely made up the author's name, stating it as fact.

Google returns the correct author's name.

Having to constantly verify the AI's bullshit, doesn't sound like something I want to pay for. (I used a free version of GTP4 via hugging face for the book test).

I primarily use gptel configured in Emacs right now, so I’ve found myself with a chat buffer always open.

https://github.com/karthink/gptel

In the last couple of weeks I’ve found it really useful chatting through ideas about a parser combinator library I’ve been working on. It also really helped me understand some of the finer points of monad lore. I genuinely don’t mind when it gets things slightly wrong first time, I’ve found the interactive process much more productive and educational than finding half a solution on StackOverflow and then being on my own.

I use it several times a week to extract structured data from chaos. It’s truly excellent at taking a specified template (CSV, JSON or XML) and fleshing it out. Sometimes I do this for test data entirely generatively.

This isn’t a work thing I guess but it’s generated what I think are extremely high quality D&D campaigns to play with my kids who have just started out. Things like that really help increase the amount of quality time you have as a family when you’re busy.

I’ve also tried many things that have failed. I often want help with cryptic crossword clues, sometimes even after giving up and getting the answer I don’t quite understand the construction. But neither does GPT. I have tried to use it to structure parts of my classical history reading but I’ve found it no better than Wikipedia in general and its utter refusal to have opinions about anything is slightly maddening.

- weekly meal plan: I let chat gpt decide almost all my meals for a week given specific macro distribution parameters and I made a small script that takes the ingredient list and automatically orders them from the supermarket

- explore tech ideas: when I have an idea about how to improve a specific part of a system by using something I have little to no experience with I use chat gpt to explore topics, get to know which topics should I study to properly understand the solution and validate different alternatives

It's super useful for working with terrible APIs such as Shopify. Since it's trained on programs where people have figured it out from trial and error, it saves me a lot of time.

I think all of our stories will look the same, we all ask about small problems, to get an answer as accurate as possible. It did help me in something else. If someone has a weight problem, you can ask ChatGTP to plan you an eating schedule. I've lost 6kg in 2 months now by eating healthy food. If someone is interested what questions I've asked, I've asked ChatGTP to create me a weekly meal schedule, where for my current weight, activity, height, I will be able to lose 0.5kg per week.

I used it to write a regular expression to find some strings (I can never remember the syntax). I used it to double check some logic that I wrote “here is my input data, is this what my output should look like based on these rules.” I guess it could’ve written the code too. I used it to figure out what bike chain I needed. Asked a tax question, and the rest has been f-ing around. gpt-3 is very bad at chess, comes up w banal fiction, but is good at synthesizing non-fiction.

It’s been an amazoing productivity booster. Both in terms of reasoning capability and how it improves my context switching ability from one language and set of problems to another.

I’ve used it as a much smarter SO and Google for understanding existing code and getting suggestion how to solve some low-level problems in code as I’ve mainly working on fixing a lot of bugs (not my own code) and it’s in a programming language and libraries that I’ve got almost no previous experience in. It’s not always accurate but the amazing thing is that it’s somewhat steerable, but you need to have enough experience and understanding to detect subtle errors.

I’m only feeding it small snippets of code and sometimes we only chat about toy examples that are related to what I work on so I don’t have any major concerns about data leaks or hacks.

I’ve also tested it’s ability to do BDD, TDD, CI/CD and some more esoteric things such as formal verification with TLA+. My experience have been it works pretty good for any thing which have good amount of examples and related content. It’s actually a very good tool for learning as you can query it for issues you’re having while learning.

The only issue is it’s not up to date for leading edge stuff because of it’s cutoff time.

Lots of tasks that I understand, but where I'm not familiar enough with the details to be productive. Anything that's easier for me to read than to write. Anything where I'd otherwise be stumbling around trying to build a template for myself.

Here's an example capturing a session from earlier this week:

https://twitter.com/JoshCMandel/status/1638723030154203138

In work it’s common for me to put together working prototype software to demo feasibility of some approach.

The knowns are libraries, languages and sometimes sample code.

Usual workflow is lots of Googling and reading documentation to get something out in a few days.

GPT saves me lots of time researching and has effectively replaced Google and StackOverflow. It allows me to design a plan of attack from “use these 3 libraries to do x” to a working prototype which I can then iteratively refine. It also is good at answering technical questions about library and language features. For example: “I have a pandas data frame, show me how to loop through it and access columns 3 and 4”. Once I see the API call is iloc I can research more.

However there are a few issues with GPT:

1. Makes up APIs that don’t exist.

2. Uses APIs incorrectly.

3. Not up to speed on the latest APIs, or maybe chooses not to use them?

For example I’m working with a library that has two functions: create_group() or get_or_create_group(). GPT seems to not acknowledge that get or create exists.

Some usage tips:

1. I usually tell ChatGPT in my first question is: “don’t respond with too much text or detail. If I need more clarification I will ask.”

2. Use Shift+Enter to formulate my initial question in detail. For example if I say “let’s write a Python app” it will respond with “sure Python is a great language to…”. So give it enough detail to get to the point.

My favorite usecase for ChatGPT right now is generating code in obscure languages like Security Rules in Firebase, bash scripts, ffmpeg and Image Magick manipulations

I've used it for the following concrete tasks:

- Github CI pipeline for running tests on a pet project. To the best of my knowledge it was 100% successful with no edits needed, but it was stupid simple.

- Starting place for Jest tests on the same pet project. It didn't give me 100% correct suggestions, but it greatly reduced the mental barrier of using a new technology and writing tests with mocks in an unfamiliar language (typescript)

- Determining how hot a mosfet will get under a certain voltage/amperage with no electrical understanding. I asked for many different mosfets and it got the data sheet numbers frequently incorrect. Super helpful going from 0 to figuring how what to look for on a data sheet and plugging those numbers into to formulas to determine how hot different mosfets would get. (context, this was for a 3d printer)

- Writing a Fresh Prince of Bel Air opening rap scene parody for a board game. I would give it the ideas, it would write the lyrics. Eventually I strung together a bunch of it's lyrics and asked it to make it better. It did by making stuff rhyme better. I had to shorten and change some lyrics to fit to the beat. Way easier than writing it from scratch.

I'm having it generate code of course (it hallucinated the ability to write a minecraft mod for bedrock in C#). Other than that, it wrote a Discord bot for me.

I have also used it to make data tables comparing cars. Silly stuff like TCO$ per kW per kg. I found the best way to make a spreadsheet was to ask it to generate A, B, C column headings and numbered row headings. Then asking it to emit the excel/gsheet formulas instead of calculating the values. You have to double-check everything, but pasting the table into gsheets and just using the formulas bypasses any numerical issues. Excited to use this approach to tackle another problem (and get Wolfram integration set up, that looks amazing)

Summarizing and explaining science concepts to interested kids. It's good at simplifying language. I was trying to put a young kid on Wikipedia, even the simple english version uses too much jargon. This can break down the jargon, answer questions about specific details for clarification, and even calculate real world examples. It's a pretty neat science teaching tool.

Just used it to plan a classy bachelor party. Full itinerary, transit times, estimated costs, it provided suggestions on places to go based on my suggestions, really impressive.

It's been a real mixed bag for me. The other day I tried to get it (GPT-4) to generate shader code to create a ray with a pannini projection, and it failed over and over and over again. No amount of reprompting or nudging got it anywhere close to fixing the problem.

On the other hand, it can explain certain complicated concepts extremely easily. I like asking it questions when I just want a general answer as opposed to something that must work.

I've so far used successfully it for:

  - Larger, more annoying reformatting tasks when Copilot isn't cutting it. Stuff like turning Go's variable dumps into JSON. I'm too lazy to write a tool to do it really.
  - I had it take a small legacy interface and wrap it in a nicer one. Passed a handwritten test suite with flying colors.
  - Coming up with arcane sed, jq, cut, etc. commands. Generally it is great at getting me 90-100% of the way to a solution in query/command languages that I just don't have a compelling reason to learn deeply.

It has come up short for me when:

  - I asked it for advice on architecting a new service, and it mostly ignored my requirements. It just looooves suggesting Kafka, Spark, etc for any task.
  - Tried to use GPT-4 to make a rather large rewrite of something into Rust, and it couldn't do it (even its context window was too small). Compressing the code did not help; it elided all useful parts of the code since it had no "budget" left.

> For generating reports : I dumped a few SQL definitions in the prompt, then started asking questions like: "Write an SQL statement to check how many users signed up last week?".

Then used these commands in Postgres.

> For proofreading, adding emojis and changing tones : ChatGPT doesn't have a personality. It's prose generation is not bold. So I write the text myself, and ask Siri to proofread it, add emojis etc.

I call ChatGPT Siri. It doesn't seem to mind. It never acknowledges it though.

> For repetitive typing tasks ⌨: Convert Markdown text to org mode, add a quote around all variable names, add a tab in every closure.

> For writing code : This is a hit or a miss, but I have realized that Chat GPT points me to correct APIs, or variables that I can look up on Google

> For learning paths : I'm learning Emacs and cooking. I tell GPT my current state, things that I know, and the place where I want to be. It fills in the next steps. Not ideal, but I hope this improves. This will make AI an excellent teacher.

> For generating content ideas : It kills the writer's block. Chat GPT generates enough good ideas for me to pick and write tweets on. But I refrain from using GPT content directly because it's bland.

GPT (Generative Pre-trained Transformer) is a powerful language model that can generate human-like text, complete sentences, paragraphs or even longer text based on a given prompt or input. Here are some ways you can use GPT to be productive:

Writing: Use GPT to help you write articles, reports, essays, or any other type of text. You can provide GPT with a topic, and it will generate a coherent piece of writing that you can use as a starting point. However, it's important to note that the output from GPT should be used as a tool for inspiration and should always be reviewed and edited by a human to ensure accuracy and readability.

Content Creation: Use GPT to generate ideas for social media posts, blog titles, headlines, and email subject lines. This can save you a lot of time and help you come up with catchy and engaging content.

Language Translation: GPT can be used for translation of text from one language to another. You can input the text in the source language, and GPT will generate the translation in the target language. However, it's important to note that the quality of the translation may not be perfect and may require further human review.

Personalization: GPT can be used to personalize content for customers by generating personalized emails, recommendations or marketing messages based on their previous interactions and behavior.

Research: Use GPT to help you with research by generating summaries or insights on a given topic. You can input a research question or a keyword, and GPT will generate relevant insights based on the available data.

It's important to note that while GPT can be a helpful tool for productivity, it should be used with caution and always reviewed by a human to ensure accuracy and clarity.

I just used chatGPT to help me write some Powershell scripts. Here’s the kicker though. I have never wrote a Powershell script before and I have only read some on the basics of functions. However, I know enough about programming in general to still tell where the problem could be. It’s been nice so far. It’s never gotten it right the first time but coding is always an iterative process. We did get there much quicker than I would have alone. It essentially taught me Powershell.

One takeaway though is that (at it current level) I still don’t think it will replace programmers. It’s initial solutions sometimes go in the wrong direction, but because I could still understand the code it wrote, I was able to get it on the right course pretty quickly. It often went like: hey i don’t think you should be technique/structure X could you replace it with Y, and it would often get it much closer after that with some minor bugs to fix.

Overall it actually felt a lot like pair programming with someone who knows all the documentation but not always the best way to approach the problem.

Last night, I used GPT-4 to help me design a stereo matrix mixer circuit.

First, I used it to help me make sense of the datasheet for a crosspoint matrix IC, and when "we" determined that the IC I was planning to use didn't support some of the functions that were critical to my design goals, it suggested a number of alternative ICs which might work, along with listing potential tradeoffs that might impact my design.

In the process of doing this, I had it make suggestions on how I could use various combinations of resistors and capacitors to buffer (clean up noise) that might impact my signal. At one point, it generated a schematic so that I could see what it was talking about, and it was correct.

At one point, it imagined some functionality on an IC that does not exist, and when I asked it "on a scale of 1 to 11, how confident are you that the AD75019 supports EVR?" (essentially, variable resistance across all 256 crosspoints) and it went back to the datasheet to correct itself, saying "on a scale of 1 to 11, I am 100% confident that it does not support EVR", which is about as sassy as you can get while still being obsequiously polite.

During the entire conversation, it not only suggested that I verify our conclusions with a qualified EE, but kept recommending that I check out existing commercial products. Not because it didn't understand I was building a device, but because it kept telling me that purchasing an existing product would be less painful than the time, expense and difficulty of building my own.

I believe that it was (strongly) implying that my time is valuable and that I should stop while I'm ahead. I ended up ordering an Erica Synths Matrix Mixer today, though I still might build my dream device. I call that productive.

For general troubleshooting, it's helpful to ask things like "How do I troubleshoot a slow OS X finder?" How do I migrate mail messages and calendar items from one Office 365 mailbox to a new Office 365 mailbox with different email address in the same tenant? Can I use group policy to configure certificate based authentication for Microsoft Outlook? Where do I start when trying to renew and replace an api certificate on aws?

Also, for leisure I've been using it for gaming. For example, "Do you know about the survival game Rust (yes)?" Then follow up questions, how many beancan grenades to break a metal door? How long will it take to craft 500 sulfur worth of 9mm ammo? I've learned quite a lot from it but when it said I can use a grappling hook to scale a high external stone wall, I noticed this flaw. There is no grappling hook in prod/vanilla Rust, so I told it so, and it corrected itself to say it may only be available on modded servers.

Also I ask it a lot of medical questions, treatments, symptoms, long term outlooks, over the counter treatments etc.

I've mostly been using it to write shell scripts, or to answer specific/hard to Google questions about various libraries/tools.

Sometimes I use it to help me come up with names for projects/classes, sometimes I use it for debugging help (X doesn't work, why not?)

I think I could get a lot more out of it if I was more creative. It's an incredibly valuable tool already (on a similar level as intellij for me)

I asked him to create new plausible scenarios for an X-Ray training program I'm writing.

It was not THAT plausible, but it filled the placeholders I have in my UI quite well and he actually used other words related to anatomy than thos I provided in an example.

Also, I asked him to output the resulting scenarios according to a vague json schema and he complied. Copy/pasted it in my JS front and it went without a hitch.

I'm experimenting with something really cool at work:

There's an open source software project called "Metabase" that we use for reporting. I want to add some functionality, but its code is on Clojure, which is a language that I don't know and don't REALLY care for learning (it seems to be a sort of Lisp dialect, parenthesis heavy). So, I am using GPT as my code writer. I tell it how I want to modify a function or add functionality in a very precise way and it writes the code. Then I compile and run the resulting code to see how the changed worked.

BTW, when starting this project, it occurred to me that a transparent "babelfish" sort of translator that translates code form X programming language to your language of choice automatically when you open a file in VS Code would be amazing. I dream of the day when I can just do `code .` in the Metabase code directory and I can program in my language of choice while GPT transparently translates it to proper Clojure code.

I feel that with an advance enough GPT we could make it work.

I had it come up with a new data concept that was quite funny:

Data Flambulation Coefficient (DFC)

Unveiling the groundbreaking Data Flambulation Coefficient (DFC), a novel concept that redefines how we perceive and analyze the intricacies of our data. DFC evaluates the "entwining" of data, delving into the deep interconnectedness between seemingly unrelated data points. This sophisticated metric combines the principles of glomerosity and the innovative dinglemorf analysis, offering unparalleled insights into the underlying structures and patterns of complex datasets.

By leveraging the Data Flambulation Coefficient, businesses and researchers can reveal hidden nuggets of zibberfex and unriddle vast swathes of yaltrizite, leading to more robust decision-making and a competitive edge in data-driven landscapes. DFC is set to become a staple in data analytics, providing the means to unlock the full potential of data's intertwined narratives.

It's solved what I call my "45-year coding problem":

With GPT-4 I solved a problem in a completely new way that I had been iterating on for over a year, in a total of about 90 minutes.

I've tried to start coding (which I love) dozens of times over 45 years. By the time I was in my mid-twenties, I found it was always to use as a tool; I had a problem to solve, could it help?

Pre-Stack Overflow and internet, it wasn't efficient, because I kept running into time-consuming headwinds and had get the problem solved. End coding project.

Once Google Search got good, I was able to move a little farther forward, but still found it too time-consuming for any one problem. And in my attempts at coding, the farther I got, the more time-consuming the headwinds were. It's almost as if you need to spend many hours/week over several months learning so you can tackle more actual problems than sample problems. But I didn't know what I should be studying.

I’m obligated to pick up a new bioinformatics DSL and have been asking GPT4 to translate my current code (bash, go, python) into this language. It is not perfect but it gets me close to what I need, with some editing.

Sometimes I ask it to make music: https://github.com/carbocation/jinglebells

I wrote plugins for Code to add TSDoc comments to all my methods. Also, right click refactor and comment. It's nice now. Soon it will make me unemployed.

GPT and other language models have the potential to enhance productivity and efficiency in various industries. Developers and professionals can use GPT with other tools and APIs to streamline their workflows, automate tasks, and gain new insights. For instance, socialbiogen.com that I made is a web application that uses openAI api to generate personalized social media bios based on the user input. While GPT can also be used for writing or correcting code, it's important to note that language models are not always accurate. Overall, these tools have become increasingly valuable for automating tasks, generating ideas, and saving time.

I use it to do bizarre linguistic stuff with my writing (prompts such as: "convert this sample of modern day English to french-Canadian gibberish as heard by an 18th century poet at a pub"). I use it to mess around with my parents. I use it to help with difficult math problems, sometimes. For me? It's been a terrific assistant.

I tried out the wxWidgets library recently and used GPT to generate examples on how to do things. Thought it worked excellently and got 99% of the code right.

In the past, I'd have used forums to find examples. There were still some forum posts about wxWidgets on Google, but I got the impression they were hiding most. Either way, GPT had them on demand.

Like others here, I’ve used it to mostly replace the Stack Overflow and Google type queries I was doing before. It has also been a good replacement for reading through documentation when I’ve started work in a new library of coding language. It’s the best “rubber duck” (other than a real human) that I have ever had.

However, other than sometimes being confidently wrong, I have found that it sometimes will suggest solutions that rely private functions. I assume this is because it’s learning from the source code itself. This is has been especially true in Android SDK libraries. On the other hand, it is impressive when I inform it of the private function use and it corrects itself.

It's a very good doc search. if you are working with new systems, it's insanely efficient for learning

-I stopped using it -I read detailed blog posts about its new abilities -I am reading the transformer paper. If I play with it, it will be on my own machine. -I am worried at the rate of progress. I am worried that the saftey assurances from openai are theater. -If I worked at openai and thought it would become dangerous and that the saftey work was theater, I would continue to work there because it is futile to try to stop at this point. The best you can do is hang around and hope that you can figure something out down the road, instead of unemploying yourself and having no influence. - I consider any internet connected thing ai material. A Tesla with over the air updates is a weapon.

I haven't really started using it, but I'd like to.

I have a PDF file of every web page I've ever read/found interesting since the last century. This collection of about 70,000 files turns out to be a massive database of things I'm interested in.

I'd love to have an AI analyse this collection, and do things with it. What, exactly, I don't quite know - recommend other subjects that are similar, find aspects of the things I'm interested in that I don't know about yet, maybe even find similar sites to those found in the PDF metadata that would fill in gaps in my knowledge. Not sure yet how that will work, but I'm thinking about it regularly - usually whenever HN prompts me with Cool AI Thing of the Day™ ..

I've had some great uses. I've had it clean up language in customer facing documentation, had it provide great examples for things like KPIs and OKRs, I also had it take a story about a beloved pet and write prompts for a children's book.

I haven't used it for coding but I've definitely found it really useful in writing. I'm not a bad writer, when I put thought into it but I find it's always useful to have a collaborator and ChatGPT has given me one that's always available.

I've also done some less productive things like work out architectural plans for a chicken coop remodel I need to do. I also got into a discussion about where and how to do french drains on my property, so we can plant more.

I started a new side project this weekend and began by explaining what I wanted to GPT4 and having it write the code, then I'd assemble it, fix a few bugs and it all basically worked.

I created 2 main components:

- Login with Github flow that saved the users username + organizations to a Google Sheet

- Signing a message and verifying the signature is correct.

Both I'd estimate would have taken me ~10 hours to implement (20 hours total, I'd never done either task before). With the help of GPT4 it took ~4 hours, so a 5x speed improvement.

The code it gives is pretty similar to what you'd find reading a tutorial or stack overflow questions, it just tailors it more to my use case.

I have asked ChatGPT tax questions, some of which I knew the answers to and others not. I think it’s a great summarizer if the spammy blogs out there.

It’s great for bash one-liners with flags and OS-specific nuances.

Haven’t really been able to use it for really advanced things. But maybe someday.

"Dear ChatGPT, please submit perfectly acceptable and politely worded PR's which elegantly fix all the software bugs in Debian's bug database: https://www.debian.org/Bugs/ I'm referring to all bugs for the upcoming "bookworm" release. The PR's should fulfill all of the Debian project's policies and guidelines. For the AMD64 and ARM64 architectures. Much appreciated.

By Monday March 27th, 5:00pm +08, 2023. Thanks!"

https://mstdn.ca/@sbb/110083097733267112

- Asking coding questions is the most common use I have seen. But it doesn't always give the correct answer. That's fine. At least it points to the right direction. Since it has the context it's easier to ask follow up questions.

- Finding new tools. Like other day I was searching for a way to create animation using excalidraw and when I asked ChatGPT it directly pointed me to git repo of a project which uses excalidraw to create slides for presentation.

- ELI5: It does do decent job for this. But not always.

- Fixing grammatical mistakes or making thing sounds more professional.

- Finding alternative for some solution.

- Generating digram for some flow via mermaid code or digram for code.

I wrote this some time ago about how you can use GPT to write good code: https://sudssm.medium.com/make-chatgpt-your-intern-not-your-...

It's actually too slow at the moment. I find myself asking it something and then opening another tab and doing a conventional search. Often, I'll get the answer faster via conventional search.

At this point I'd prioritize speed over new capability.

I’ve tried. Recently I’ve been using to try to improve my resume and asking it for suggestions and information on certain technical subjects related to my career and current situation.

At the end of the day, none of the output it’s offered has necessarily impressed me, though some of the ideas from that output has influenced me an how I write my resume.

I also tried to see if could generate come code similar to something I used in a recent side project. It utterly failed to produced correct code, but perhaps the gpt4 model would do better. So far I’ve been using it as search engine as I will admit, it’s done better than google and friends at giving me the information I ask for,

I fed it some documentation I wrote that had 2 FAQs and asked it what additional questions a user might have after reading the page. It came up with 10 additional questions, about half of which I added to our actual FAQ section!

Plain old Bing Chat - which I feel a bit better about using because I'm not paying for it and not contributing to the problem that way - used for its original intended purpose of search. Compared to trying out keywords and reading through the results myself, it's faster to ask the question, let Bing read the pages, and let Bing summarize the results to me.

I recently got access to Anthropic Claude, which I don't feel as squeamish about using as I'd feel about paying $20/month to OpenAI and helping them destroy the world, so if there's more that can be done that way maybe I'll find it out soon.

Bash scripting. I've been doing it intermittently for over 20 years but my tool set knowledge is limited. ChatGPT often shows me new ways of doing things in Bash that I'd never have thought of. It's downright brilliant.

* writing powershell scripts

* How to write js code using d3 to animate swapping of two bars in a bar chart? (No other context given, it gave me a v good, working answer)

* what is a convertible note?

* In this it failed - can u help me setup auth to my react app using nextjs, for deployment in vercel?

* next I'm planning to ask several questions to understand state of the art in child education, there are many methods like montessori, Waldorf etc and I want it to provide a summary

* I need to keep adding this flag to make npm build to succeed, plz tell why I need it and how to solve the real problem (it explained beautifully and now I'm using yarn as a result)

A while back, I mentioned in a thread that I have found ChatGPT to be quite useful for correcting grammar and spelling errors (https://news.ycombinator.com/item?id=34781888).

Later, when they released their API, I developed a CLI tool for this purpose (https://github.com/pncnmnp/grammatical). Note that it is not flawless, but it works well. It has improved my writing productivity, both for blogging and emails.

I pasted some headers (some of them very long, in multiple chunks) and asked the bot to write me a summary of what the API does, and what could be used to make it better. Answer were spot on. Free documentation! If you also paste the source, it can give you a documentation for a particular function as well. Same for rather complex Makefiles.

Otherwise I do like others, I use it as a quick stack overflow for uncommon APIs (to me). Or completely random questions, knowing the answer might be dicey.

It has replaced google at about 90%, I only use google to verify, and not all the time.

As a non-judgemental sidekick. It helps with flesh out a random thought, it helps me understand a random coding problem, it helps me see why a vuln exists in a particularly difficult-to-read piece of code, and building outlines for reports and presentations that I'm too lazy to deal with. It is also starting to replace the random Google searches I used to do.

To boil it down, it's my "10-minute task" time saver.

And my use of it really picked up when I started using GPT4. It's head and shoulders above GPT3.5 in terms of quality and clarity of output.

Coding. Best example was an obnoxious 3rd party C++ API with header, and sample code that was more confusing than helpful. I fed the header and sample code to chat-gpt (was not too many lines) and then asked it to write a sample application that did X using the API. It almost worked, and needed a bit tweaking, but removed so much of the effort of trying to parse hundreds of lines of pseudo-gibberish to get to the few API calls I needed. I'm not going to name the API here. You know such things exist, and sometimes for good historical reasons.

Yesterday I just used it for the first time instead of checking the Postgres docs for some obscure JSON operators. I just asked it this:

"I have a postgres database with a json column with the following structure: [1, 2, 4, 4]. How do I query the database in SQL to retrieve all rows where the array in the json column contains the number 4?"

And it gave me a wrong answer at first (worked for strings only, not integers), but quickly corrected itself after I pointed out the mistake. I had working, testable code faster than if I had checked SO or browsed the Postgres docs.

I've asked GPT-4 about the human brain and specific metabolic pathways every day so far. If you ask it for answers in jargon like written in a textbook or a journal it will provide an obscene level of detail that you can then verify.

As a "domain specific words" generator for building up a glossary, it can't be beat. From a prompt perspective I have to tell it that we are both world class neuroscientists but it knows more about this specific question than i do. Then I tell it to reply using correct jargon for the domain like that written in a textbook

To me it is most useful when I have a singular issue with a bounded piece of code. Like a method, a single algorithm. A nasty SQL query too sometimes.

I don’t use if often (once a day maybe) but when I do use on problems I know it is good at I get really good answers. Oneliners to things my code is taking 20 loc to do, or some simplification I overlooked. But I have to be careful about what I give it.

I know I am better with architectural issues, but I suck at puzzle-like algorithmic problems. Don’t like them either, feels like a machine should do that and now it does.

I've used it mostly as a tool to look up documentation or man pages. Instead of opening hundreds of tabs to do my research I just have a thread going with a theme in ChatGPT. Of course, I don't blindly trust what ChatGPT gives me but I know it's around that ballpark and I double check and do more googling or research if I'm ever in doubt.

Funnily enough, I haven't used it as a tool to learn completely brand new things as I can't gauge if what's ChatGPT is giving me is 100% accurate.

As a journalist who needs to read very technical research papers and interview scientists involved, in order to make the implications of that experiment accessible to the lay person, I find Chat GPT actually excels at cutting through the impenetrable academic jargon that can put you to sleep before you can discern the bottom line - and also explaining the equations etc in straightforward language.

(My prompt: Explain in simple terms, or Explain for a university level reader).

I'm finding it very helpful.

Maybe not too productive but I often ask:

* "How to not be behind the technological advancements",

* "What are the future-proof jobs after the AI revolution",

* "How to get to the cutting-edge of my field".

I like it because I can paste an SQL query in and it has an immediate understanding of the layout of my database (only columns and tables included in my query of course - but I can also describe other tables too in the conversation). Then I can have a conversation with it and it can help troubleshoot my issues. I'm terrible with JOINS and it's been helpful in getting me the data I need.

GPT Development Services are hard to come by! We provide end-to-end solutions so you can transform your business with cutting-edge GPT technology!

We, at Rather Labs, provide GPT development service. If anyone is interested, you can contact us: https://www.ratherlabs.com/gpt-development

It easily bridges over sections of code and documentation that are otherwise tedious to produce. I can just write a dense rambling explanation, and it'll decompress that into a piece of text or code that includes all the well-known bits that I skipped in my description.

Also fun is just to write out a hypothetical library idea, and walk through a whole hypothetical development process to validate it, steer it in alternative directions, and find the more challenging points for improvement.

I have a basic understanding of multiple coding languages, but I don't have the time to learn the exact syntax or commands for each one. ChatGPT has given me so many tips and scripts on coding in VBA, M query, DAX, JavaScript, and more. I'm currently using it to customize a Power Apps solution, which would take me 10 times longer without ChatGPT.

Been pretty useful for discovery of SDK functionality in open-source libraries, that otherwise takes a bunch of time Googling the answer for. For example;

- Using golang, how do I write a custom marshaller for uber/zap

- Given a list of protogen.Files, how do I parse protobuf options and their values

Unfortunately the generated code is more often than not incorrect or uses non-existing API methods, but can give an idea of methods to use or where to look in the official api docs.

Email rewrites, translation between English and French, asking some very old functions and structs from the 1991 version of ls.c, teaching it some RPG rules and then play text games, generating boilerplate code for work and side projects.

So far only using the free version and experience is good. I might buy the plus subscription but so far lacking any hard requirements. I particularly hope it gets better teaching me system programming as sometimes it BS.

Not directly. testrigor.com helps me to write test automation. They use GPT to generate tests based on test description

I have a chat always accessible with the below prompt to help me learn another language:

Can we use this chat to translate between English and xyz? If I enter an English word or phrase, please translate it to xyz. If I enter a word or phrase in xyz, please translate it to English. If my spelling is incorrect, please attempt to correct it, offer your suggested spelling, and then proceed to translate.

I've asked ChatGPT for solutions to coding problems I haven't encountered before, as well as error messages that aren't immediately obvious. This augments Google for me.

I'm also working on a UX for AI to make people more productive when creating things: https://inventai.xyz. Subscriptions are nearly done, which are needed to actually generate content.

I use it to write tons of boilerplate code in random flavour of the week languages I am dealing with at work or on hobby projects. e.g. nginx/ansible/powershell/golang etc.. weird codebases your thrown back into a few years later. I know what I want, I just forget the exact syntax of how to get it done. Sometimes its wrong and I have to correct it, but half of the battle is knowing when its bullshitting.

* Porting code (generally code that I've written) from one language or framework to another. For example, porting Python to JavaScript. [1]

* Getting started with a new platform. For example, describing the problem, and having it create a template in a front end framework, CSS framework, API generator.

* Creating instructional materials. Pasting in code and generating explanations, assessments, and grading rubrics. [2]

* Generating the first pass of API documentation, READMEs, test suites, and configuration files. Modifying configuration files. Finding configuration options based on NL descriptions.

* Quickly generating examples of API uses that are specific to my application. Finding out what libraries and APIs are available for a use case, based on an NL description.

* Learning what algorithms exist for a problem. Generating implementations of these in different languages, or that are specific to my code or data structures.

* Rarely-used system administrations commands. For example, how do I flush the DNS cache on macOS Safari and Chrome? (Questions such as this are actually better on Perplexity.ai than on ChatGPT.)

* Pasting in error messages or descriptions of problems, and asking for solutions.

* Tie-breaker questions about what to name a file, function, or set of functions.

In general, I find that it takes a lot of the drudgery out of programming. (Similar to Copilot, but for a different, generally more macro, set of areas.) For example, I asked it to solve a geometry problem and generate a test harness for both interactively and batch testing it. It's solution to the problem itself was a non-starter, but the test harness was great and would have been involved boring work in order to write.

I also use it to generate emails, project proposals, feedback, etc. I don't think it's ever come up with anything usable, but seeing what's wrong with its attempt is an easier way for me to get started than looking at a blank page or searching for examples of the writing form on the web are.

[1] https://notes.osteele.com/gpt-experiments/using-chatgpt-to-p... [2] https://notes.osteele.com/gpt-experiments/chatgpt-code-expla... [3] https://notes.osteele.com/gpt-experiments/discussing-an-ardu...

I just used this to create and integrate a new component(layout) in one of Hugo's theme. I wanted to view lists as cards and using GPT saved me a lot of time. Im not a frontend developer and i dont know how to start writing some code, but i am able to verify and modify when i have it. Its also a lot faster to get proper responses or directions through chatGPT than from google.

With the understanding that it's only trained up to Sep 2021, I'm using it to spot check for any libraries that have flown under my radar, or any other methods of doing work that I usually do, but in a different fashion.

Do I always get stuff that I can apply? No, not really. But given that discoverability can be low for things like that, it's usually helpful at finding me things to, at the very least, look into.

I've been using chatgpt/gpt4 in a ways.

-Created a jupyter extension for code completion, auto commenting, and an error handling assistant. -Automated my email to auto draft responses to important emails. -Automated my email to auto summarize important received emails. -I've manually used it to create lots of documents including correspondence, marketing material, and code generation.

I have been using it to reword messages that are displayed in an UI. I write out the information that the message needs to convey and ask it to generate a simple and concise piece of text that does the job.

A month or so ago, I tried asking it some really specific questions about the Linux kernel and it did not generate anything useful. I assume it must have gotten a lot better now with the larger model.

Not part of any workflow per se, but I’m planning a trip to NYC this month and asked it to generate an itinerary that includes certain sights along with suggested places for lunch/dinner and subway directions. What it produced blew my mind! I simply couldn’t have done what it did on my own.

I use GPT4 for Powershell mostly. It does all kinds of gymnastics that I could have never even dreamed of. I am far more Jobs than I am Wozniak. GPT is like having a WOZ with you all the time. Granted it is one who takes hallucinogens every once in a while.

It's helping with fast explanations for pretty much anything.

But the drawback is... it enables lazyness for the sake of "productivity", developer quality might significantly drop by spending less time doin propper research on their subject, and on top of that it's output is not necessarily correct but many will find it reliable again out of lazyness or ignorance.

I’m not using it at all. Until I can run it locally and guarantee my interactions with it are entirely private and under my control, I won’t touch it or related services. I’m constantly surprised to see people who talk so much about privacy and data protection using such systems. That said, when self hosting is an option I’m very excited to use it.

My big question is, are people at OpenAI actively using GPT as part of their work? Are they getting a productivity boost because of it?

ChatGPT is giving answers that we have already given - all over the web, on specialty sites like StackOverflow etc. - possibly with some adaptation and combination. So, I prefer to contribute - both questions and answers - to public venues rather than huddle with the AI.

Also, I'm not willing to register with OpenAI, let them keep my interaction records etc.

I am using it to write documentation for the product that I'm building. It's an app builder and requires extensive documentation. I spit out thoughts on to ChatGPT and ask it to structure those thoughts into a structure and complete sentences. It would take me 3x time to structure it myself. But I wonder if this means I'm getting lazy?

ChatGPT is really good with ‘text’. So I’ve been trying to experiment with different file formats. Some notable ones:

- copy paste (emails for reservations) or type an event or multiple events and ask to convert it into ‘ical’ format. Copy output and save into file, import into you calendar

- convert natural language into json , yaml or other structured text with custom fields

I use it to give me the perfect functions for any task I can dream up in Google Sheets. Some conplex functions seem like a novel I never would have made, but it works very well so quickly and when it errors, it nearly always can debug. It understands the Maps for Sheets extension well and I'm trying to teach it to master GPT for Sheets.

A while back, I wrote a simple CLI-wrapper around OpenAI's API that I'm using daily (https://github.com/maxvfischer/askai). I use it as an addition to Stackoverflow to ask quick programming-related question straight in the terminal.

I have a lot of experience in Operations / debugging of web apps, and the plumbing around them, and only a little bit when it comes to writing software. I'm finding chatGPT to be very useful to me as someone who basically knows what needs to be be done to make something but doesn't know the design patterns well.

Have it write windows bat files to automate my computer use. Some, would have taken hours to write but chatgpt delivers in a few seconds. I ask and it delivers. It's not always right but it does not hurt to ask.

I'm now looking into other areas where it can help me automate easy but tedious tasks.

Some people still doubt its usefulness. I don't.

I use GPT4 to workshop different ML ideas. I ask it to combine different ideas from the literature, for example.

"How can I use denoising diffusion with this approach?" etc.

It's great to be in a critical mindset, because being creative and critical at the same time is much harder than being critical.

I use the socratic method and really dig in with it.

Follow up question, how come discussions like this rarely mention virtual assistants like Siri/Alexa/etc?

So many use cases overlap, there’s potential for improvements but Siri still struggles to understand context and gpt has no way to access my calendar (at least in a way that I’d like). I guess this will change fast?

I use it for finding description of the products that I have to upload to the website of the company where I'm doing practices. So interesting because y used to give chatgpt tips to find the specific results that I want

Mind blown example from last week:

  Implement the following repository interface against sqlite in Golang. The method receivers should be defined on a struct called “repo”. 

The code used prepared statements and worked out of the box. I wrote unit tests to verify.

I've been using it to explain my own code. If it can explain it in a way that I believe someone else can understand it - then I know my code is legible to the next developer that will look at it. Also, the process is a sanity check for me and also helps me to further refactor the code.

I use Kagi as my search engine, however, Kagi has moved to a limited amount of searches for my price tier. So instead of searching "how do I do x in y?" I tend to ask ChatGPT instead. As SQL is my main language I tend to get really quick feedback if the code it supplied was valid or not.

I gave a UX person a snippet of debugging code to paste into the console, but didn't notice that the chat app ate the quotes around a string. GPT was able to fix the snippet for him. SO far this is the only case where someone I know managed to use it for something useful in practice.

I use it to write boring German letters that don't need a human touch. It saves me the trouble of finding the right words in a foreign language. It made dealing with the bureaucracy a lot less dreadful.

I think it might be good at answering "why" questions since Google completely gave up on that.

I’ve been trying to use it to come up with crossword puzzles and word-finding puzzles. Not quite there yet, but maybe more prompting would help?

I have used it to help come up with lesson plans for various topics. In general the lesson plan sucks, but it may contain 1-2 things that I forgot to cover.

I’m new to writing contracts and agreements, and ChatGPT has replaced Google as a point to jump in and start building these documents without having to wade through pages of unhelpful SEO tuned search results and then pick and choose clauses from sets of often irrelevant samples.

One convenient usecase for me is to generate model classes from a sample JSON document: "please create me a java class using lombok from this JSON: {...}"

Also vice versa: "create a JSON document with sample data from this java model class: "public class Person {String name; ...}"

I've been using it as a really specific codegen tool. I give it a chunk of a Swagger doc and ask for a TypeScript React hook that validates the API response using zod, and it gets it right pretty much every time. It's nothing I couldn't do myself, but it does it faster.

I have not googled coding stuff in a few weeeks so Stack Overflow and its snotty gatekeeping is dead. That "Please post full line" is answered now. And thankfully lots of people like YOU will soon be out of a job.

Is there a big difference between chatgpt and chatgptplus? I use chatgpt for routine things every day (some basic word smithing, looking up how to use libraries, etc) and it is already quite good. What does the 20/mo get me that I don't already get with the free version?

I use it to motivate myself for trivial tasks such as setting up systemd, cron, dockerfiles, nginx, apache, etc. It cannot finish the job, but it feels very cyberpunk and makes me want to complete menial tasks.

Update: Thanks your your responses. They inspired me to create an app from scratch using GPT-4. https://news.ycombinator.com/item?id=35312404

I use it to find characteristics of the products that I have to upload in the company website. It's interesting because I give chatgpt specific tips to find whatever product I want.

I'm a writer (copy, social, all-purpose) at a startup. I've been using GPT4 via Lex.page to generate crappy first drafts which I then improve and expand. It can speed up the process quite a bit, but needs handholding and someone to add in personality.

I've only just started trying Co-pilot out, and when it suggests the line I was about to type out anyway, it's a real time-saver. It is less useful on more-complex code, and it's just abysmal when it tries to fill in comments for me.

My primary interest is in researching recent events, and it is pretty much useless for that

Since it's a transformer model, I use it to... "transform" the data. - Change raw citation into bibtex entry - Fix spelling mistakes - convert csv file into json (though you can do it without employing trillion parameter model) etc.

I ask it for functions in Google Sheets and it gives me the perfect thing I never would have come up with myself, sometimes functions a mile long. I also explained the Maps for Sheets and GPT for Sheets extensions, and it is a master of both.

I get many ideas which requires coding, launching and PoC. I wasn't able to do as I don't have time or work force with me. i believe I can do it now. Will use the GPT or copilot-x and start launching fast and prototype ideas.

1. Built a recommendation engine

2. Asked it to convert many curl requests with funky headers to Elixir code using Req/Httpoison.

3. Massaged data from weird structures to other weirder more custom structures.

lots of other things. it's been a real boon to my productivity.

For doing simple tasks such as help writing unit tests.

I need to often give some examples from other tests. I need to make many edits, but it spits out enough to have a basic boilerplate-ish template and speeds up my work by at least ~25%.

I recently write up a description of a relatively simple algorithm in markdown. Then pasted into ChatGPT-4 and asked it to write python for it; it was correct except for a small error. Saved me an hour or so.

Mentioned in another thread - I use it to write unit tests for me.

I give it a function, tell it to write a test and it largely gets it right most of the time. I have to tweak it but the time spent is a lot less than if I did it myself

Personality engineering a team of NPCs as an audience for reading and encouraging me to write my fiction, helping to build an IDE for writing, deploying website CI/CD pipelines writing Dockerfiles, APIs, etc.

I think HN should really have a GPT mode, where you see the first comment made by GPT on any article. This would be a good way for us to evaluate how serious this technology actually is/has become.

My most common usage now is asking it to come up with names for functions/classes. You can iterate on the names it come up by telling it why you don't like the names it proposed.

Lately I’ve been doing a lot of very deep discussions with GPT-4 about design issues I’ve had, and brainstormed ideas on how to improve them. In these discussions, GPT-4 has been able to really dig into the details and grok the problem space, and has surprised me with the quality and brilliance of its ideas and suggestions. Some of these I have tried, things that I would not have thought of, and it turns out the suggestions really helped solve the challenges I was facing. To me it’s like working with a brilliant person who can only communicate via text, can’t look anything up on the internet, and can’t remember more than a few pages of text at a time, but aside from those limitations is a genius.

Lots of people talk about generating code with Chat GPT, but to me its real value is in having deep detailed discussions about design problems.

It’s been so successful at this that recently I gave GPT-4 the full interview design skill assessment that I give to engineers when I interview them at Microsoft. GPT 3 wouldn’t be able to handle this, but what GPT-4 did here astonished me. My assessment is that this is a principal level performance. It didn’t have to do other things that normal candidates have to do but for this raw skills assessment of design skills it was spot on. It would have impressed me even more if it figured its final solution out from from the beginning, but that’s what it gets for blurting things out before thinking about them, which people do, too.

The important thing I’m communicating here is not that I am impressed because it’s amazing that a computer can do this stuff; I’m impressed at what it has done here compared to almost every human I’ve ever walked through this question with. The approach I used here is the same I use when asking candidates this question, because in addition to testing their ability to code, I’m looking for how well I can understand the candidate’s ideas, and how well they can understand and then apply my own ideas when I ask them to take a different approach on certain things than they were thinking of themselves. This is one area where many great coders struggle; they can code like the wind when it’s their own idea but struggle to work collaboratively. This kind of mental flexibility, ability to think of things in a different sequence or consider other ways to solve the problem after thinking of their own solution is also a required skill often in real-life meetings and other collaborative settings. I’d rate this candidate as an outstanding, top-notch collaborator.

My point here is that using it only to write boilerplate code is a waste of its best value. My suggestion is to get GPT-4 with its larger token limit, and talk strategy with it. Tell it all about your biggest challenges at a level of detail that would exhaust a normal human, and talk through ideas of how to improve your world.

Talk to it about your people problems too. It’s an astonishingly wise counselor who has a wealth of positive insights and suggestions. It’s also great for elegantly wordsmithing things.

Don’t miss out on the chance to collaborate with this endlessly creative and endlessly patient collaborator.

I've been a paying ChatGPT subscriber for about three or four weeks now. One day I had a few thorny work issues, asked the free version, and it was so good I got a subscription.

Since then I've asked some about general knowledge, history, religion, geography, politics, other topics of interest. Mostly in English, but some in Portuguese and a little in Spanish. It's extremely good in all three languages.

Mostly though I've been asking about random work topics that come up every day. We use a lot of lots of systems, tools at work, and I need to write software to handle diverse areas. ChatGPT cuts right to what I need as far as: (a) general knowledge of tools and what their purpose is; (b) surveys of categories of tools, comparisons between competing offerings; (c) specifics on how to use, configure, program against various tools, query data, change things; (d) questions on best practices and pitfalls. This is mostly in context of macOS, Linux, AWS, kubernetes, observability tools, and APIs for lots of DevOps-related systems. I do lots of coding in Python, I also do a lot of ad-hoc diagnosis of situations. (We have a great DevOps team that manages infrastructure with standard DevOps tools -- my job is to build what those tools don't address so well, and also to help build out future data-engineering efforts.)

I'd say my use of Google search to find relevant articles / pages has gone down 70%. One small example today, I wanted to use `jq` to process some `docker ... --format json` output to pull out some data. I don't want to learn the ins and outs of `jq`, I described my problem and it gave me a good template I could adapt.

Any time now in scrum or other meetings, if there's any question about something, we often just consult ChatGPT during our Zoom/screen-share sessions. I think generally I have a better sense on how to structure questions and question progressions to get quick answers than some others.

I've also found ChatGPT makes up stuff sometimes ... but it's usually close enough.

One comfort I have is that, at least for now, ChatGPT can't direct the overall organization of code for the many situations I need to address, so I'll have a job for a while. It does though fill in the knowledge gap at the edges, I don't waste near as much time searching for and reading documentation and examples. ChatGPT usually has good ready-made low-level examples when I need them, and high-level descriptions of tradeoffs and best practices.

I'm "committed" to Jetbrains tools, been using them for a long time. Today I began wondering what I might be missing from CoPilot, downloaded the CoPilot plugin for PyCharm (would also work for IDEA, DataGrip, etc.). I couldn't get the CoPilot plugin to log into Github and saw that others have had similar problems in the past ... so I can't use CoPilot yet. Maybe in a week or two I'll have a basis for comparison. (I don't want to switch to VSCode.)

EDIT: word choice, minor clarifications

I needed to write a spec for a DSL I've written and I did part of it myself, fed that part to GPT4 and had it write the rest of the spec.

It required some small edits but saved me 3 hours of writing.

I have found it is quite good at configuring complex AWS IAM policies in JSON. Not perfect but it saved a bunch of time.

There are so many other examples but I truly never reach to google first anymore.

I used ti understand the US Healthcare industry as an non -US person.

I often use it to just gain ideas when I'm stuck with any situation, eg: "How to deal with non-responsive stakeholders?"

I'm currently working on a game despite not being very familiar with Unity. When I have some feature I need explained, or running into some bug in the game, I'd usually use Google and find some forum post that hopefully has a similar problem to mine and go from there. With GPT, I can just tell it the problem and get an answer, without scouring through multiple posts or having to constantly readjust my query. Yes, the information it produces might be incorrect, but I think the (time needed to verify the solution provided) is less than the (time needed to produce a search query that gets the articles you want * time needed to read each article and see if it helps me).

Here's an example regarding grounded characters sticking to walls:

prompt: Thanks! I added walls and ground to my game, as well as detection so that if the player touches the ground, they will be in a grounded state. However, when the touch the vertical face of the ground/wall, they stick to it. Can you tell me what I'm doing wrong?

response: It seems like the issue you're encountering is related to the physics and collision detection in your game. The player is likely detecting the wall as the ground, and it's causing the grounded state to be triggered when it shouldn't be. To fix this, you can modify your ground detection code to take the angle of the surface into account.

Here's a solution using the Physics.Raycast method:

Assuming you have a LayerMask called groundLayer for ground detection, make sure the ground and walls are assigned to the appropriate layers in the Unity Editor

[...further details on using angle detection on collision, as well as accurate sample code]

I can even ask it to give me the reference for the _Physics.Raycast_ method:

response: Certainly! Here's the official Unity documentation for Physics.Raycast:

[URL to official docs filtered out by HN]

Physics.Raycast - Unity Manual The Physics.Raycast method allows you to perform raycasts in your scene to detect collisions with 3D objects.

[...further information on how to use it, including an accurate code example pulled from the docs]

This just drastically reduces time-to-solution, especially when you consider you can lazily leave out information and still get a good response.

In short, I treat it as though each session is a fine-tuned search engine and get a lot of value from it, but it doesn't completely replace forums or Youtube videos, for one it can't argue with itself to provide conflicting but valid alternate solutions - I'd have to argue with it/ask it to produce those.

Me: what do you think about Robert Frost

GPT: I speak the road plausibly travelled.

- Having it write Ansible tasks for me to automate setting up my infra. - Generating test data for integration tests - Create sample data for demos and marketing material.

I was writing ffi bindings for a lib in Rust and asked it to write out all the structs for the external lib with any needed serde attributes and it worked very well.

I recently asked it to convert some bash code to golang (which I'm just beginning to learn) and it was really useful to give the skeleton with proper syntax.

Using it with PhraseExpress.com - A tool that allows me to highlight any text such as a SEO keyword and let it run through ChatGPT to create an article.

Dating, intros, chit chat Emails, bullletpoints to text CLI commands lookup, what was SO Brainstorming when I get stuck on my research

Code reviews. It takes a few tries until it gets the job done, but in baby steps it reveals stuff I didn't think about.

Last week I used Dalle to make a logo for a side project and GPT to write some Javascript for it (I’m mostly BE these days).

For business, I ask it to generate plans.

- Creating JSON out of unstructured Text.

- Writing SOPs

- write Email

- Tone Analysis

- Recommendation Engine

ChatGPT wrote my professional goals during my works mandated goal setting period.

Summarized all the comments in this page using chatGPT and grouped them.

# Programming and coding assistance

-To improve code by making it simpler or reducing duplication.

-To generate code for straightforward tasks with clear-cut objectives.

-Writing code in a language that one is not familiar with.

-To get help with design patterns in software development.

-Spotting libraries, methods, or alternative ways of doing work that people usually do but in a different fashion.

-Writing code or fixing bugs in a specific algorithm, method, or SQL query.

-Automating email to draft responses and summarize important received emails

-To generate test cases, identify performance issues or bugs in code, and convert layouts from Android XML to Compose.

-Help with writing unit tests by providing basic boilerplate templates and speeding up the work by 25%.

-Building bindings for a library, creating simple schemas for a microservice, and solving a one-to-many relationship problem.

-Using OpenAI as a virtual assistant to set reminders or access calendars.

-Writing code: OpenAI's GPT can provide suggestions on APIs or variables to use, saving users time researching and helping them write more efficiently.

-Writing commit messages: Some users use GPT to generate commit messages for their Git repositories, saving time and mental energy.

-Learning programming languages or technologies, such as PowerShell, by using OpenAI to create initial solutions that users can refine and iterate upon.

-Generate complex queries or configuration files

# Automation and efficiency in day-to-day tasks:

-Summarizing and finding answers to specific questions on various topics, including tax questions, recipes, and movie suggestions.

-Transforming data, such as changing raw citations into bibtex entries, fixing spelling mistakes, or converting CSV files into JSON.

-Outsourcing corporate emails to ChatGPT to convert them quickly and easily.

-Document search and learning new systems.

-Converting code: using OpenAI to convert code from one language to another, like from bash to Golang.

-Model classes and JSON: using OpenAI to create a Java class using Lombok from JSON and create JSON from a Java model class.

-Writing specifications: using OpenAI to write the rest of a specification after writing some part of it, saving time.

-Generating boilerplate ADS docs for detection content, converting rules between various query formats, identifying and normalizing security data, and brainstorming how to approach novel detection use cases in the cybersecurity field.

# Language learning and translation:

-To learn a foreign language by getting errors corrected and grammar concepts explained.

-Asking questions to improve writing, better understand concepts.

-Language learning: using OpenAI to learn conventions in a programming language one is not familiar with.

# Creative writing and brainstorming:

-Generating plausible scenarios for various training programs or creating standard terms of service for an app.

-Generating ideas for creative tasks, such as brainstorming, writing, and lesson planning.

-To lower the emotional-resistance barrier to doing creative tasks and improve the quality of the output.

-Creating crossword puzzles and word-finding puzzles.

-Creating lesson plans for various topics.

-To workshop different ML ideas by combining different ideas from the literature.

-To do bizarre linguistic experiments with writing prompts.

-Creative naming: using OpenAI as a creative partner to help with naming things like a data warehouse.

-Generating names for projects or classes and debugging help.

-Write SOPs, write emails, and analyze tone.

-Aid in the writing process, including transforming thoughts into presentable versions.

-Writing contracts and agreements.

- Regex

- SQL queries

- Bash scripts

- Specific code snippets, often for APIs

- Explaining code snippets

- Google Apps Scripts

- Pub Quiz questions (not very successful but some are ok)

I am recording all my calls and building a Q&A bot over the transcripts.

bing for browsing and solving problems in code or otherwise. I still use a my old Brave browser for Youtube and most other browsing still.

I will probably start using ChatGPT again now that theyre adding plugin support

Earnestly thinking about non-computer based revenue.

My bash scripting game is now 1000% betterer thanks to GPT

Code generation such as converting json to F# types.

documenting and explaining existing code , then as a follow-up improving it

Writing Emails, mostly.

By not using it

I haven't been using it for much besides simple problems that I don't feel like trawling through SO or banging my head against for 30 minutes. Things like shell one liners for text processing/searching files/etc.

On larger tasks, I've not found it particularly useful, although I haven't had a chance to try it out with GPT-4. Previously, when I would ask ChatGPT about solving a particular problem, it would be terribly broken. Maybe GPT-4 is better.

That said... even though the code was broken, it was helpful in that it gave me a skeleton of what a solution would look like, especially if it was a problem domain I had no experience in.

For example, I wanted to do a little project to extract text from PDFs, including PDFs that were basically image scans, so I would have to do some kind of OCR. I'd never done anything like this before. I'm sure I could spend time Googling and figuring out which libraries to use. But instead I asked ChatGPT.

The solution it gave wasn't great, but more importantly it pointed me in the right direction with the libraries it used and some examples on how to use it.

Aside from programming, I've also used it as a "study buddy" since I'm going back to school and working on my masters in Computer Science. That's been much more successful. For example, I will give it questions from study materials handed out by the instructor (like previous exams or quizzes) and say "We are reviewing paper X in this class. Here's questions from a previous exam. Please generate questions like this to help me prepare for my upcoming exam."

or "Here are questions from a previous exam and my answers. Please evaluate my answers and provide feedback."

or "Here are questions from a previous exam, please quiz me in a similar format"

Also working on projects for class, while I won't ask it to solve the problem for me, sometimes I'll bounce ideas off of it. Like... "I know there's an algorithm to do X, but I don't know the name of it. I don't want you to write the algorithm for me, because that's cheating, but please tell me what the algorithm is called and if possible point me to a good paper describing it."

Lastly, I recently used it while helping someone update their resume (with permission). I removed all personal information and asked ChatGPT-4 to help me make it pop. We had a little back and forth conversation on ways we could improve the resume, and when we were done it was pretty damn amazing. I'm pretty good at doing resumes, but me + ChatGPT was better than me alone.

Apparently it did a bangup job, because every interviewer went on and on about how good the resume was and how impressed they were.

GPT is helping me write a D&D adventure. I'm not very creative so it helps me. If I don't like elements of the story it's very responsive to changing elements.

It's surprisingly good at remembering earlier details. Occassionally it will forget things but another prompt tends to fix that.

For example I'm about to plan Chapter 4. The broad story so far is that the adventurers are doing some tasks for a friendly NPC and during that will slowly uncover clues to the BBEG, in this case a cabal of vampires who plan to plunge the world into darkness.

Prompting it with:

    Let's plan Chapter 4. Can you produce a short table of suggested titles and themes?

It produced:

    Title Theme
    The Vampire's Lair The adventurers infiltrate the vampire lord's castle and uncover his dark secrets.
    A Deadly Dance The adventurers must navigate a treacherous ballroom filled with traps and minions.
    Into the Abyss The adventurers descend into the catacombs beneath the castle and face unspeakable horrors.
    The Final Showdown The adventurers confront the vampire lord and his minions in a dramatic battle for the fate of the realm.
    Beneath the Moonlight The adventurers discover a hidden shrine dedicated to the vampire lord and must unravel its mysteries.
    Blood Magic The adventurers face off against powerful necromancers and witches who serve the vampire lord.
    The Betrayal The adventurers must confront a trusted ally who has been working with the vampire lord all along.

In table form.

Now it's got a little confused, because in chapter 3 the gang already infiltrated the castle and confronted the vampire lord, but another prompt will fix that.

Prompting:

    In Chapter 3, the adventurers already infiltrated the castle and dealt with the vampire lord. Can you reproduce that table assuming the vampire lord is no longer a threat for now (even if he remains at large)?

Produces:

    Sure, here are some possible titles and themes for Chapter 4, assuming that the vampire lord has been defeated (at least for now):

    Title Theme
    A Web of Deceit The adventurers uncover a plot by the cabal to take control of a powerful artifact or location.
    The Hunter Hunted The adventurers are pursued by an assassin or bounty hunter hired by the cabal.
    The Fallen Hero The adventurers discover that a beloved hero or figurehead is secretly working with the cabal.
    An Ancient Evil The adventurers stumble upon an ancient artifact or tomb that holds the key to defeating the cabal.
    The Betrayer's Gambit The adventurers are double-crossed by a trusted ally who has been secretly working with the cabal.
    A Race Against Time The adventurers must complete a series of challenges or tasks before the cabal can enact their plans.
    The Final Confrontation The adventurers engage in a final showdown with the cabal's leader or their most powerful agent.

(again in table form)

Which are great suggestions, now I can pick one and ask it to write the next chapter based on that, at which point we can flesh out more details.

Deleted comment to reduce ridicule…

i'm not.

Every morning I ask it whether it has headache. Then I smack it with a monkey wrench.