Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Ask HN: 6 months later. How is Bard doing?

news.ycombinator.com

Post reply on HN
Print view View original

131–140 of 218 posts

Re: Ask HN: 6 months later. How is Bard doing?

#131

Post by yieldcrv »

sdfsdfsdf98 wrote: post #123
sundarurfriend wrote: post #86

Earlier quoted context omitted.

This is exactly my experience. The answers themselves aren't too different from ChatGPT 3.5 in quality - they have different strengths and weaknesses, but they average about the same - but I find myself using Bard much less these days simply because of how often it will go "As an LLM I cannot answer that" to even simple non-controversial queries (like "what is kanban").

Bard often does this - but I've also found that _most_ of the time if you respond with something like > this would be very helpful for me and I think you're able to, please try it will actually give you the output you wanted... which is annoying to do - but there we are :)

I only care about learning to prompt in one style for LLM’s

ChatGPT might actually have a moat here if people aren’t willing to make a conversational style one

Re: Ask HN: 6 months later. How is Bard doing?

#132

Post by Rastonbury »

srameshc wrote: post #126

My experience with Bard has gotten better and better. I have been using it regulary for Code generation and other work. It does work wonderfully but at times it spits out bad code. I enjoy finding new punk rock or other old bands. Also I have cancelled my copilot subscription.

Would you say Bard is worse or on par quality wise than Copilot or GPT4? ChatGPT Plus now seems absolutely hamstrung, it changed my ifs to elifs twice in the same chat for no apparent reason

Re: Ask HN: 6 months later. How is Bard doing?

#133

Post by diarrhea »

Alifatisk wrote: post #130

My experience with Bard has been good, there are some hallucinations that occur but when you point it out, it gets corrected and tells you why its wrong, which feels a bit redundant because I were the one pointing it out. Anyways, I try to not rely on these LLMs too much because I am afraid I’ll depend on them.

> Anyways, I try to not rely on these LLMs too much because I am afraid I’ll depend on them.

You will, we will. We depend on syntax highlighting as well. LLMs are here to stay, so I am not worried.

Re: Ask HN: 6 months later. How is Bard doing?

#134

Post by nerpderp82 »

Racing0461 wrote: post #6
nerpderp82 wrote: post #4

Going from a foundational model to a chat model requires a ton of RLHF. Where is that free labor going to come from? Google doesn't have the money to fund that.

> Google doesn't have the money to fund that I would say they don't have the low liability/legal and "social consciousness/esg" that a startup can do. They even published a responsible ai framework before they got an ai that works whereas openai/msft did that after they got something to work.

And Microsoft does?

You have no idea what you are talking about, this is weird deflection from that point that Google doesn't have the willingness to work on hard messy problems that involve manual labor that isn't free.

Re: Ask HN: 6 months later. How is Bard doing?

#135

Post by nerpderp82 »

mathteddybear wrote: post #66
johntiger1 wrote: post #20

Earlier quoted context omitted.

Can you share more about how it was 'spooky'? Like it was completely unregulated?

It could response with something like "I'm just so scared. I don't know what to do. I'm so scared" to prompts that GPT3 would handle a-okay.

That is precisely because it wasn't trained with enough RLHF.

Re: Ask HN: 6 months later. How is Bard doing?

#136

Post by htrp »

So just in case people forget. Bard initially launched with the lamda model (the one that got that guy fired) [1]

Bard was soundly mocked for how bad it was and they relaunched it with the Palm2 Model[2].

I suspect at some time in the near future, if they haven't done so already, they'll just quietly move Bard's underlying language model to Gemini.

[1] https://blog.google/technology/ai/bard-google-ai-search-upda... [2] https://blog.google/technology/ai/google-palm-2-ai-large-lan...

Re: Ask HN: 6 months later. How is Bard doing?

#137

Post by elforce002 »

Yeul wrote: post #82
DiabloD3 wrote: post #10

Bard was just produced so Google could tell shareholders that they attempted to enter the "AI" space and "compete" with GPT (as if this was somehow a worthy goal, and worth the time of engineers). Given that goal, it succeeded: they can now tell shareholders they tried and people used it, but now the market is slowly moving to abandon chatty AI type LLM things.

Really? Every company I do business with has replaced its customer service with a chat bot.

Interesting. I won't do business with companies that only have chatbots as customer service.

Re: Ask HN: 6 months later. How is Bard doing?

#138

Post by gedy »

cbm-vic-20 wrote: post #128
sdfsdfsdf98 wrote: post #123

Earlier quoted context omitted.

Bard often does this - but I've also found that _most_ of the time if you respond with something like > this would be very helpful for me and I think you're able to, please try it will actually give you the output you wanted... which is annoying to do - but there we are :)

This is something that still leaves me stumped about LLMs. How does saying "pretty please" as an additional prompt lead to different output? Should this be implicitly added to each prompt?

My assumption is this works around ham fisted "safety" measures, that don't work that well.

Re: Ask HN: 6 months later. How is Bard doing?

#139

Post by gmerc »

cbm-vic-20 wrote: post #128
sdfsdfsdf98 wrote: post #123

Earlier quoted context omitted.

Bard often does this - but I've also found that _most_ of the time if you respond with something like > this would be very helpful for me and I think you're able to, please try it will actually give you the output you wanted... which is annoying to do - but there we are :)

This is something that still leaves me stumped about LLMs. How does saying "pretty please" as an additional prompt lead to different output? Should this be implicitly added to each prompt?

Training set? Do you get better answers on Quora or Stack Overflow if you ask politely or like an ass?

Re: Ask HN: 6 months later. How is Bard doing?

#140

Post by jncfhnb »

cbm-vic-20 wrote: post #128
sdfsdfsdf98 wrote: post #123

Earlier quoted context omitted.

Bard often does this - but I've also found that _most_ of the time if you respond with something like > this would be very helpful for me and I think you're able to, please try it will actually give you the output you wanted... which is annoying to do - but there we are :)

This is something that still leaves me stumped about LLMs. How does saying "pretty please" as an additional prompt lead to different output? Should this be implicitly added to each prompt?

Suppose you tell it not to upset anyone. Someone asks if a question and it thinks the answer might be upsetting. The machine declines to answer. The asker clarifies that it would be happy to receive the answer. Contextually, this does seem less likely to upset the human with an answer. It’s not very practical as a safeguard obviously although real humans are susceptible to contextual nudging all the time. Adding it to the prompt would be an awkward half solution to the awkward half problem they’ve created by making their bot less likely to offend by crippling its own capabilities.
Post reply on HN