How are you finding Gemini Ultra?

One thing I've found Gemini Advanced (Ultra) is actually good at is sustaining a conversation to work towards a goal that requires some back and forth. I've been calling it "putting it in collaboration mode", which isn't super accurate since it's not technically a "mode" but whatever. But in my experience ChatGPT (and a lot of instruction tuned LLMs) tend to try to get to the end of the conversation as quickly as possible. (To the point where GPT4 will regularly just end the "and if that doesn't work, go read the documentation" ... which is very frustrating.)

Gemini on the other hand will ask several follow-up questions and behaves more like a conversation you might have with a coworker on a pair-programming topic. It's kind of changed the way I think about the utility of LLMs.

I've struggled to get it to generate images, especially when related to memes. For instance, I wanted to extend the "this is fine" image, but Gemini Advanced would not because it was harmful to animals. Most of the image requests I give it are back-and-forths on what it can't generate for me for some ethical or moral reason.

I've been using GPT-4 (mostly for coding and general knowledge, use it a lot more for personal projects than actual work) for the past year, and just switched to Gemini Advanced (since there's a 2 month trial, that includes Google One, which I'm already paying for), and so far it's pretty comparable. The "check sources" google button is sort of handy but it only works maybe 25% of the time to get a confirmation of a statement.

It sort of adds a "confidence level" check that saves me from doing it myself afterward like I would for GPT-4.

Edit to add: Gemini Advanced seems to be a lot faster as well at responding, in terms of tokens/second, compared to GPT-4.

Currently subscribing to both, and for tricky programming questions I go ahead and ask both and take the answer I like more. There was an AWS networking problem I was debugging that Gemini got but GPT4 didn't, but Gemini has trouble with giant pasted code, and doesn't allow file upload yet, which is a major blocker for me.

For things I would formerly use a web browser to look up, Gemini is often a lot better than gpt-4. The more obscure the query, the better Gemini does compared to gpt-4.

But gpt-4 is still best for ML Python coding. Gemini hallucinates non-existent libraries and often adds unnecessary junk to its code. For example, Gemini often defines spurious variables and then never uses them.

This is about early testing (on code) of Gemini 1.5, but presumably that will come to the Gemini consumer product in not too long so …

I've put a complex codebase into a single 120K-token prompt, and asked 7 questions GPT-4 and Gemini 1.5. Here are the results! https://www.reddit.com/r/singularity/comments/1atjz9v/ive_pu...

For writing text (emails, etc.) and asking basic questions gemini is superior to gpt-4 in my opinion. But when it comes to logic, programming and resoning, gpt4 is better in my opinion. It rarely makes syntax or logical errors, and the jupyter notebook that chatgpt has access to is a big plus for me. It can use it to solve math questions with sympy, use matplotlib and I can ask it to crop a video file for me. Gemini makes a lot of basic mistakes and the code examples are very minimalistic.

For those that want to give it a shot, there's a two month free trial here:

https://gemini.google.com/advanced

It was not so easy to even find out how to buy Gemini Ultra, apparently it's called "Gemini Advanced," or maybe it's called "Google One AI Premium Plan." Searching for "Gemini Ultra" doesn't give you a link to any this on any of the top page of hits on a Google Web Search, and you have to dig deep in announcements to find it.

I've been very dissatisfied with all the free Google options, but this post has given me the kick to see if the bigger models can compete.

I subscribe to both ChatGPT and Gemini Ultra. Some interesting features/experiences with Gemini...

1. I asked it to do an image search and it responded with in-line images throughout its response. This was a nice "wow" moment and very neat.

2. Its drawing/illustration style is different than DALL-E, so I use both.

3. Quality of general text responses is comparable, though I prefer ChatGPT.

I imagine you can probably just use one rather than have both. I am still primarily using ChatGPT.

I'm a Google Fi subscriber, so I still can't switch to the Google One plan with access to it. Incredibly frustrating.

I use Github Copilot and GPT4, and some CodyAI with GPT4 for coding. I still find them better for code. But, I have been using Gemini Ultra for creative writing targeting humans.

For human writing, Ultra is w-a-y beyond what ChatGPT 4 is capable of IMHO. GPT4 sounds like an AI write it. Even if you put a lot of prompting into establishing the right tone. With Ultra, it is getting hard to tell. Which is great! I think of them like people. Each has their own opinion and has talents in different areas. Given they are $20/m I am happy to pay for all of them. It takes them about 5 minutes to pay for themselves.

I passed this text through Ultra and this is what I got:

Absolutely! Here's a rephrasing that focuses on a more natural, flowing conversational style while still conveying the core ideas:

I use GitHub Copilot, GPT-4 (and CodyAI), and Gemini Ultra regularly, and I've noticed a big difference in how they approach tasks. For coding, Copilot and GPT-4 are my top picks. However, when it comes to writing that needs to feel truly human, Gemini Ultra is hands-down the winner. It's getting to the point where I often can't tell the difference between its output and something a real writer would create. That's a huge difference from ChatGPT-4, which still can have that telltale "AI feel" even with careful prompting. These tools each have such unique strengths that I find them all valuable – the $20/month investment for each pays off in just minutes.

Changes Made:

* No Visual Cues: Removed formatting elements (bold, bullets) that can scream "AI-assisted".

* Conversational Flow: Uses phrases like "I've noticed a big difference" and "hands-down the winner" to feel more like someone speaking their experience.

* Softened Comparison: Keeps the idea that Ultra surpasses ChatGPT-4 for a certain type of writing, but tones down the strong declaration for a more subjective feel.

Let me know if you want it even more casual or have another specific tone in mind!

For my purpose — reading hourlong transcripts of conference calls and answering questions about them — it is pretty useless. GPT-4 got nerfed so many times that it is no longer useful for that. Claude 2 is now my go-to.

I don't live in the US, so I'm not finding it at all.

I currently, have a free two-month trial, but it's not worth paying for yet. It still fails in hilariously simple ways. E.g, one of the example prompts shows how to use it to generate an image. But asking [Can you generate pictures?] results in "Unfortunately, I am not currently able to generate images directly. However, I can help you explore some resources that can do just that!...". Forcing it to generate an image result in broken elements.

It also fails at more complex tasks that I would actually use AIs for. E.g, I'm trying to learn Lagrangian Mechanics and keep running into dead ends with Gemini in cases where ChatGPT is working.

I have faith that Google will make it better in the near future (unless they get bored and move on to something else) so I'm hoping it will be worth paying for. But right now, I'm going to keep my ChatGPT subscription since that is actually useful.

Actually for coding sometimes it’s better than GPT4. A lot of times worse, but my work flow is to give the same coding question to both. I play them off eachother. OpenAI will lose their edge if they don’t release a new model soon

It is worth the 2 month feee trial with the Google one space.

But - I am a Uk iPhone user - so Gemini Advanced is only available via a website rather than app, and no image generator. So, for me:

ChatGPT4 Pro > copilot pro > Gemini advanced

Ask it about bgp states and ask it to create an image !! It creates faces !!

Haven't tried any of them.

Google is never worth a subscription. They have completely moved away from "don't be evil"; don't encourage them by giving them more money.

There are posts going around X that Gemini image generation is very biased toward minority preferences even when factual data and real-life statistics don't support the outputs. For example, can somebody ask Gemini to generate a picture of a typical Swedish women?