While I have found that ChatGPT pretty regularly outperforms Bard, I still run my questions through both, because sometimes Bard has a different angle that I like better.
I kinda liked the name “Bard”. It fit. Gemini is going to make me think of ancient rockets and ostentatious claims.
I was using Bard and chatGPT in parallel, but lately I just default to Bard. To me it's a better model with much more accurate answers, while chatGPT just gives you bombastic words.
I'm impressed with Gemini a lot and prefer it to ChatGPT. I asked what the price of Bitcoin was today and it gave me the price from several sources and I told her the Coinbase price was wrong and she checked again and said "You know what, you are right, I've corrected that."
She seems nicer than ChatGPT, is faster, and gives answers with less fluff and nonsense padding added. I think I've found my new LLM.
I hated the name Bard it just seemed like the name a of a second place LLM, I don't know how to describe it better than that.
Tried Bard a couple of times recently and was not very impressed tbh. Seemed to forget the context of the conversation very often. Like I had to repeat again and again to not show external links with previews and not give explanations to every little thing.
I'd suspect they're just trying to start over - Bard kinda got pegged as Google's dumb, not-as-good, late-to-the-party clone of ChatGPT. It got teased a lot. I'm not sure Gemini is much different (still more impressed with GPT 3.5 & 4) but I guess the name change gives them a bit of a reset.
That's interesting, because I have had exactly the opposite experience testing GPT vs Bard with coding questions. Bard/Gemini far outperformed GPT on coding, especially with newer languages or libraries. Whereas GPT was better with more general questions.
I think there’s bias in the types of prompts they’re getting. In my personal experience, Bard is useful for creative use cases but not good with reasoning or facts.
Bard is terrible, by comparison. ChatGPT feels like spontaneous answers. Google Bard will literally copy top search result answers to questions, and doesn’t answer them relevantly. It’s a bad extension of search.
I've been using Gemini in Bard since the launch, with respect to coding it is outperforming GPT4 in my opinion. There is some convergence in the answers,but Bard is outputting really good code now.
I try to glance at both, but because I do that I know that ChatGPT has severe availability problems, whereas Bard so far has not failed for me. And Bard is much faster even though superficially it can seem slower because ChatGPT blurts out the first word more quickly.
I kinda liked the name “Bard”. It fit. Gemini is going to make me think of ancient rockets and ostentatious claims.
reply