Pro: feels like it has a lot more stylistic flourish and expressiveness than chat GPT. At least in my testing so far.
Con: maybe I'm unreasonably sensitive to design, but I find chat GPT to be very to the point in a way that makes it almost perfect as a product that puts text for an and center. By contrast I find Bard / Gemini ultra to be cluttered, and too material designy in ways that are unhelpful.
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.
If it was cheaper, or part of a bundle, or included unlimited API access, I'd consider it. GPT4's high price is always in the back of my mind when I use it.
But does Bard really qualify as the second best? Gemini Pro is pretty bad. I'd choose Claude over it any day.
Gemini Ultra's claimed superiority required a mountain of prompt optimization and repeated generations to get good scores. The "CoT@32" benchmark results costs at least 32x as many tokens, probably closer to 64x with the hidden chain of thought. I don't have high hopes this mode will be affordable or fast enough for chat.
I just don't want to be hit with a wall of text every single time, it gets the point across with minimal padding (high signal to noise ratio), ChatGPT feels like it gets paid by the word and they do actually charge by token if you use the API.
As for the UI it's a take on the tried and true chat UI same as ChatGPT's, it spits the whole answer at once instead of feeding it to you one word at a time, it has an alternative drafts button, the Google it button is a nice touch and it feels quicker.
If you try Bard or Claude or character.ai they are not far behind GPT4. They might even be on par in terms of raw LLM capabilities. ChatGPT has better marketing and in some cases better UX. A lot of this is self-fulfilling. We think it's far ahead, so it appears to be far ahead.
In my experience (I work mostly and deeply with Bard/Gemini), the reasoning capability of Gemini is quite good. Gemini Pro is already much better than ChatGPT 3.5, but they still make quite a few mistakes along the way. What is more worrying is that when these models made mistakes, they tried really hard to justify their reasoning (errors), practically misleading the users. Because of their high mimicry ability, users really have to pay attention to validate and eventually spot the errors. Of course, this is still far below the human level, so I'm not sure whether they add value or are more of a burden.
i don't use Gemini for the image gen so all the negative news about it being left leaning and biased maybe true but for me does not matter that much for now.
What I use it mainly for, is to learn new concepts or brush up on stuff in Python and learn ML and Stats concepts deeply. it seems like Google made lots of improvement since they launched it as a Bard in terms of accuracy and usefulness especially when it comes to coding help.
Genuinely curious where do folks see chatGPT better than Gemini?
If I have to choose to keep one subscription, that will be Grammarly.
ChatGPT can do many things, and it’s impressive at generating text. But, people underestimate the advantage of good UX. With ChatGPT, I need to copy the text into a premade prompt or pick a GPT made to improve my writing. But, the writing style may not match what I want. Going back and forth with chat instructions is slow.
With Grammarly, I write the text, then click on the suggestions and adapt the style. It's orders of magnitude faster.
That's, to me, the Achilles heel of LLM chats: a specialized UI is more effective.
So, there is room for competition in many areas, even if they use the same LLM APIs to implement it.
While I don't doubt that chatGPT is better than the current alternatives, the fact that the author use the 20$/month version and not the free version (or both) to compare to bard is not very great. The same for giving the same value to paying 20$/month and knowing the model used
ChatGPT uses the model text-davinci-003, which was released alongside it. The previous model of the same kind was text-davinci-002, and in a comparison I read, seems to perform much less impressively. So it's not just the chat interface. It's genuinely more impressive in my opinion.
Gemini 1.5 is just a few points behind gpt-4 on chatbot arena but has way larger context size and is free to use and you can disable the censorship if you want, to me that is pretty awesome. For my uses it is much better than any other model available today, and it is free on top.
Pro: feels like it has a lot more stylistic flourish and expressiveness than chat GPT. At least in my testing so far.
Con: maybe I'm unreasonably sensitive to design, but I find chat GPT to be very to the point in a way that makes it almost perfect as a product that puts text for an and center. By contrast I find Bard / Gemini ultra to be cluttered, and too material designy in ways that are unhelpful.
reply