Live data from Hacker News

Bard’s latest update: more features, languages and countries

blog.google

1–10 of 205 posts

Re: Bard’s latest update: more features, languages and countries

#5
post #2

My ChatGPT and Bard use has pretty much flatlined. Has anyone else has a similar experience?

Yeah - more or less.

I still use it sometimes for trivial stuff like giving me recipe or travel inspiration (using the web search API), but I haven't been using it for any sort of algorithms/coding stuff.

It's useful for tasks which have a high tolerance for not being completely correct. Which is definitely a subset of all tasks that interest me, but it's a smaller subset that I originally thought it would be. It's just really hard to find out where the models are wrong when it's a complex question. If it wasn't, then I wouldn't need the tool, I guess.

Re: Bard’s latest update: more features, languages and countries

#8
post #6

I tried Bard and it feels worse than GPT-4, it doesn't follow the prompt very well. Uploading an invoice it failed to extract data, instead it responded with hallucinations.

Yes, I think it should be compared to GPT 3.5. Google doesn't really have a public contender to GPT 4 yet but this is what the Gemini project is intended to be, by the newly formed/reformed Google DeepMind team.
Post reply on HN