What is a specific use of GPT-4 that you think is remarkable?

I've got a thread going with ChatGPT about an app I'm building. It knows all of the libraries I'm using, and has seen the main App component, the Router and many of the key components. I'm asking it about every task I need to do, feature I need to implement, bug I need to fix. Basically rubber ducking with it and talking through everything I'm doing as if it were my coworker. It's reducing my time to solve problems by about 80%. I'm able to do 4-6 times as much in a day as I could without ChatGPT when I was stuck figuring out everything tediously on my own. For context, I'm a full stack developer with about 15 years of experience, so I know what I'm doing. ChatGPT is just taking care of a lot of the trial and error and figuring out how to use different libraries or implement certain algorithms.

I've been using it for long-term memory supplementation. Had a faint memory of driving around in a friend's truck back in high school and was trying to remember a Marilyn Manson song we always played.

Asked it this the other day:

> Are there any other marilyn manson songs with a crowd shouting?

And it spit out:

===

Yes, Marilyn Manson has used the sound of a crowd shouting in several other songs besides "The Beautiful People." Here are a few examples:

"Irresponsible Hate Anthem" - This song, which appears on the album "Antichrist Superstar," opens with the sound of a crowd chanting "Hate! Hate! Hate! Hate!" before launching into a heavy industrial metal riff.

"The Fight Song" - Another track from the "Holy Wood (In the Shadow of the Valley of Death)" album, "The Fight Song" features a crowd chanting "Marilyn Manson" before the song begins.

"This Is the New Shit" - This song, from the album "The Golden Age of Grotesque," features a chorus that includes the sound of a crowd shouting "Are you motherfuckers ready for the new shit?"

These are just a few examples, as Marilyn Manson has used the technique of incorporating crowd shouting in several of his songs throughout his career.

===

I'm highly skeptical of GPT/LLM as a replacement for humans at the task-level, but for search, this can't be beat. It replied almost instantaneously.

Even more shocking: I think this will seriously destroy Google and the concept of SEO. That's extraordinary considering how pivotal Google is to the internet of today. This is the beginning of the OS in the movie Her.

The fact that you can put in garbage unstructured data, ask it questions, and then "convert" it to JSON is kind of magical. It's like computers have a new analog/organic input system. [0]

Also, been recently playing with ways to generate API code plumbing without any schema layers. (Swagger/OpenAPI/Proto) [1]

[0] https://twitter.com/vyrotek/status/1640417769303977984

[1] https://twitter.com/vyrotek/status/1640142385282949121

Call center employees are pretty much as good as gone once the price comes down on GPT4. You can pretty easily give it a good prompt that allows it to answer very specific questions about your company, or interact with external APIs to schedule services, make changes based on the customer's requests, etc. Throw some Speech to Text and Text to Speech services in front and behind it, and voila you have an AI receptionist that blows literally every automated answering service out of the water today. IMO, 90% of call center employees will be out of work in the next 10 years.

I did a medical lab test the other day and I've been trying for several days to reach my original doctor who for some reason I still can't get. I don't know what to make of the abbreviations and scales on the document and I sure as hell wasn't going to visit another doctor and pay a fee to grok it without a need to or google each line to find out I have "cancer or some other random ailment".

By chance I was using cgpt for something else and I just copied and pasted the unformatted data from the pdf and voila. https://i.imgur.com/tCy1dWU.png, there is a more personal page that I didn't share that gave me a eli5 explanation for the exact problem I got checked for that I couldn't tell and it pretty much worked the same using the terms and even gave me recommendations as to what I could do next.

I think GPT4 isn't amazing (that is, better than excellent humans) at any specific task, so I doubt that many things it does, in isolation, are remarkable. Where they shine is that GPT4 and ChatGPT are really good at doing lots of menial tasks really quickly. e.g. I can ask it to refactor my code, rewrite it in a different style, add a new function etc and it'll happily do that all day.

Probably the best use case was for learning about things I didn't understand. I asked GPT4 questions about CSS Grid yesterday. With GPT4 I could drill directly into areas I was curious about and get a pretty uniformly good explanation, e.g. "explain to me more about the layout algorithm". Doing that with google is possible, but it's annoying to have to continually bounce between various shoddy articles on different websites in order to get a patchwork of understanding.

Unlike 3.5, GPT-4 is competent at translation. Not just competent; it's better than most human translators. We might not want to leave it to its own devices yet, but there's a large number of novels that were never translated, or were only translated badly.

Personally, I've been setting things up to have it translate a series of light novels from Japanese to English. Experiments through the chat interface show it's working; now I just need API access, to fully automate it.

Mostly code here, but I've found a few uses, mostly around brainstorming that I use as a starting point to further thought:

Brainstorming ideas such as around a party theme for my kids. Games we can play, decorations, etc.

Generating exercise ideas, particularly since I don't much like gyms or common methods

Helped me to understand some medical side effects of thyroid issues and the medicine I'm taking. Actually I learned from it that Iron interferes with my medicine, and I was taking vitamins at the same time as I was taking it. Seems minor, but my brain's definitely more active after changing things.

We just started a business, so ideas around sales tactics, what to include in a business plan, etc

Getting my mind going with questions to ask for a Bible lesson I teach around a specific passage. Apparently it can pretty much quote an interpret any passage I've given to it and generate questions, in different styles or levels of depth.

Having it explain or find interesting tidbits around the ancient Greek in a bible passage. This one surprised me. Apparently it understands to some degree declensions, parts of speech, verb tenses, etc. It's not 100% correct here, but maybe as correct as it is with code. I'm not an expert either, just graduated seminary, so it's a nice support

I've been using it as a discussion machine and a way to cut down search.

My usual loop used to be:

1. Search for X

2. Review documentation and other websites that come up

3. Learn from my review and further refine my search

4. Continue steps over and over until I get what I want

---

My new loop is:

1. Ask ChatGPT about X

2. Use the words that ChatGPT returns to me as search terms

3. Review documentation and other websites that come up

4. Learn from my review, further refine my search, and talk to ChatGPT about it

5. Continue steps over and over until I get what I want

I initially thought that using ChatGPT in such a fashion would lead to a longer amount of time - especially since I'm adding a new tool to my "loop".

Instead, finding and learning what I need is much faster. My old loop I would do 3+ times. The new loop with ChatGPT takes 1-2 times.

When you aren't familiar with X it becomes difficult to know what to search for. Even if you have the docs in front of you, you need to know key terms to search through the docs for.

ChatGPT makes finding key terms to search for much, MUCH easier. Fact checking ChatGPT (for the most part) doesn't take me that many cycles.

I want to share a personal experience with GPT-4 and other AI tools that has helped me a lot, given my recently acquired physical disability.

My creative and critical thinking are still in great shape, but I've been struggling to execute my ideas because of my physical limitations. For example, I used to paint as a way to deal with traumatic experiences, but that's no longer possible for me.

I got depressed and frustrated, being no longer able to transfer traumatic memories out of my head.

I found a workaround using Stable Diffusion and ChatGPT. By doing this, I can recreate my paintings in my own style without having to physically paint them. It's now part of my weekly routine and has been a real support for my therapy and PTSD.

Another thing GPT-4 has helped me with is managing anxiety attacks. I'm not good at coding, it's simply a skill I'm not good at, but with some assistance from GPT-4, I made a simple browser game using HTML, CSS, and JS. This game is now my go-to distraction when I feel anxious and is easily accessible on my phone.

GPT-4 has also made everyday tasks, like writing letters or emails, a bit easier for me. I can shave off a few minutes here and there that way each day, which is a lot of time I can do stuff I enjoy if you add them up over a year or longer.

While these benefits may not seem groundbreaking to everyone, especially if you're healthy, they've made a significant difference in my life and for me personally, and I think that is remarkable.

I'm also not good at asking other people for help, especially for stuff I managed to do on my own for all my life.

So if I can ask AI Tools to do stuff for me instead of taking up a friend's lifetime, it helps me to keep a sense of independence and being able to take care of myself.

I cut and pasted my child’s school’s multi page complaints policy without reading it myself, then asked it to show me the stages I need to follow as a sequence diagram and it can up with this:

@startuml actor Parent participant "Class Teacher" as CT participant "Head of School" as H participant Clerk

== Level 1 ==

Parent -> CT: Informal Complaint CT -> H: Meeting Request H -> CT: Meeting Scheduled CT -> Parent: Meeting Scheduled Parent -> CT: Attend Meeting CT -> H: Meeting Summary H -> Clerk: Meeting Summary Received

== Level 2 ==

Parent -> Clerk: Formal Complaint Clerk -> H: Formal Complaint Received H -> Clerk: Response Preparation Clerk -> Parent: Formal Complaint Response Parent -> Clerk: Request for Level 2 Meeting Clerk -> H: Request for Level 2 Meeting Received H -> Parent: Level 2 Meeting Scheduled @enduml

I've been using it to refactor my code.

I paste in all the code that it needs context for, tell it how I'd like to refactor it (e.g. there are two concerns, split them into their own structures). It then gives me a high level of what it'd do, I review and then tell it to implement what it said.

I tried this yesterday in golang with some gRPC calls and while it seemed to hallucinate a couple details, overall it did a pretty good job. I think part of getting it right will be to guide it a little more.

I'm building my own product so don't have to worry about getting company approval etc for this.

Also, language learning - I'm learning German atm and plan on asking it to list the x most common nouns in each gender (der die das) and then generate example sentences that use each of the nouns and so on.

It can explain stuff to you in exactly the way you need to, and walk you through problems. You can ask it to create quizzes / guided questions for you which helps in organizing your own thoughts. Another application I find quite remarkable is asking it for good prompts for image generation models. The biggest benefit is that you're not starting from zero when entering a new problem space / domain.

Truthfully... what's most remarkable to me is it not saying, "just stfu, you idiot" after me asking it question after question about stuff i want to know more about.

There has been countless times where I'll read it's response of, "sure, here's..." and it just blows my mind that i have the ability to barrage something with questions and it won't get tired of me doing so.

it puts a smile on my face.

I asked it to help explain the Birthday Paradox to a colleague who was struggling to understand the math behind it.

I gave it the requirements and just copied and pasted.

https://jsfiddle.net/k8L9eyf7/5

Give it access to a Python repl, show it how to send HTTP requests, how to take look at images of webpages if it needs to, and how to spawn new instances of itself - give it a budget and tell it to make money for you.

I'm using it to write WordPress plugins that can be used in place of expensive yearly subscription plugins.

Populate open world videogames with real living characters that evolve to your way of gaming.

Apparently somebody tested chatgpt 4 as a d&d DM and worked really well, so this coupled with AI voice acting could lead to exceptional results in the game industry.

Write unit tests, document code, optimize code, explain code. I've tried Python functions and React code. It even converted a class based React component to a functional style component!

Finding lots of value in drafting emails, especially for topics or asks I'm not as used to dealing with, like asking for extensions or blaming other teams for blockers. Obviously takes a few iterations ('be less verbose!') but I get a lot of value in seeing a couple different ways to word the request and how to frame the background facts to come to the conclusion I want.

Started using it as a coaching tool for new hires who aren't used to the world of corporate memos yet.

I used to build my own little wiki / knowledge graph as a fun project to see what it was capable of.

You feed it a topic and ask it to return a list of topics that are related to the parent topic. Repeat for each child topic, set a max depth and you can generate a topic tree about anything. Always asking for it to use JSON as the output.

I then had GPT-4 write an encyclopedia style entry for each child topic with nice formatting and links to actual wikipedia when possible.

Neuromancer was published in 1984 and I think we are finally on the verge of creating constructs.

The future of GPT could be like a construct, or an AI embryo. Something you can purchase that will consume every piece of data you have ever produced - every text, comment, journal or blog. Then it will consume every piece of data you have consumed - every book, movie, song or headline. An AI that can be taught to respond as if it believes what you believe and loves what you love. Something that can be a convincing copy of you to represent you to the outside world.

People who only interacted with you online might never know the difference.

1.: It's the first time I'm seeing a chatbot who could easily replace the human layer.

Chatgpt understands tons of languages.

So I highly prefer to write things up like "you can change a username by going to this ui and click this and than that".

Or anything in-between.

Even if chatgpt only takes care of translating and creating a proper support ticket.

2.: Text understanding. I have plenty of tasks were a human would need to do things for me like "pull out all features of this building and make a list out of it" before I can verify it.

3.: I can already see the use case of fine-tuning my own agent with my own data. Now it's actually worth it to write proper documentation or architecture decision records. Basically doing brain dump because after I can just ask it things like "why do we use angular?" "Because you tried out react and didn't like it"

Two things I find remarkable:

1) I’m ~50% faster at coding

2) Jailbreaks. It’s exposing in a reproducible way how people are persuaded / tricked into bending or breaking rules via persistence, role play, and confident instruction. Presumably from a corpus of text where these techniques have worked in real life.

Rewriting text to be more fluent or readable. For all the (many!) people who need to create documents in English but aren't native speakers, GPT-4 is quite effective at rephrasing a technically correct but un-idiomatic text into something that's much better.

There are a lot of use-cases that aren't possible at current pricing and model access.

For instance, we're working on a number of text classification features, but the inability to fine-tune makes it very difficult and expensive.

Sorting by personality. Every search engine I tried was useless. I guess nobody's written that exhaustive article yet.

Sort by personality? Yep. I asked it to pretend to be a clinical psychiatrist and then asked it to tell me about celebrities personalities that closely matched "calm, thoughtful, and introverted".

I've been running similar experiments with creating groups of actors' responses that conform to groups of personality types: the four humours, blood type, etc...

I can't really wait for tooling to visualise complex technical concepts into nice animations and static images.

Imagine describing how some system works, what it consists of, and get architecture images + process animations.

Write my PhD thesis, even incorporating the written and oral feedback of my advisor, which I record and use as input.

Yes it was a bad joke, one I did not think I could make just 1 year earlier.

On the occasion I do editing for certain documents on behalf of non-native English speakers. This can take up to two hours per document ordinarily. ChatGPT reduced this to 15 minutes, and almost all of that is just proofreading the output, waiting for it to respond and copying and pasting.

my daughter uses it to explain homework problems. Google search routinely fails for this. Chatgpt gives her the answer, but explains in detail how it got the answer.

marketing team is using it to create baselines for articles/blog posts.

you can do a search for "product manager chatgpt prompts"

my controller is using it to look up finance stuff including answers to questions about tax law. They will then follow up by looking up the first source articles to verify, but chat gpt can give correct answers.

HR is doing the same thing

when I run into problems trying to figure out how to do something in an application chatgpt works better than web searches, watching stupid videos, and especially the built in help for the application etc.

I have using it as my copyrighting assistant, especially when I have to write long copy

Retrieve information from public technical chats to provide Q&A on programming languages, technologies, engineering approaches and so on.

1. Quick code reviews. 2. Generating tests. 3. Good for dumb questions, that I'd hate asking a person.

I'm generally just faster coding.

Look up what is code for plumbing. It can be difficult to find what is code unless if you are a member of IAPMO.