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

ChatGPT Explained: A normie's guide to how it works

jonstokes.com

Post reply on HN
Print view View original

11–20 of 144 posts

Re: ChatGPT Explained: A normie's guide to how it works

#11

Post by Nevermark »

imhoguy wrote: post #6

The biggest drawback of LLM is that it never answers with "I don't know" (unless it is some quote) and it just brings bullshit hallucinations which human has to reject as wrong. Thus it is mostly useless for anything serious. Personally I use it to beautify some text, but still have to do a bit of correction to fix b/s or missed context.

This seems like a great opportunity for some good old fashioned adversarial training.

Post train one LLM to please another LLM, that rates the quality of the first model's responses and calls it on any bullshit! (And vice versa.)

Re: ChatGPT Explained: A normie's guide to how it works

#12

Post by IIAOPSW »

Nevermark wrote: post #11
imhoguy wrote: post #6

The biggest drawback of LLM is that it never answers with "I don't know" (unless it is some quote) and it just brings bullshit hallucinations which human has to reject as wrong. Thus it is mostly useless for anything serious. Personally I use it to beautify some text, but still have to do a bit of correction to fix b/s or missed context.

This seems like a great opportunity for some good old fashioned adversarial training. Post train one LLM to please another LLM, that rates the quality of the first model's responses and calls it on any bullshit! (And vice versa.)

Stable diffusion (of bullshit).

Re: ChatGPT Explained: A normie's guide to how it works

#13

Post by adamnemecek »

I'ts like an electric circuit where the residual stream provides the concept of a feedback analogous to the trace in traced monoidal categories https://en.wikipedia.org/wiki/Traced_monoidal_category.

Attention is a recurrence relationship that gets gradually pruned.

Re: ChatGPT Explained: A normie's guide to how it works

#14

Post by simooooo »

adamnemecek wrote: post #13

I'ts like an electric circuit where the residual stream provides the concept of a feedback analogous to the trace in traced monoidal categories https://en.wikipedia.org/wiki/Traced_monoidal_category . Attention is a recurrence relationship that gets gradually pruned.

That didn’t help a normie at all

Re: ChatGPT Explained: A normie's guide to how it works

#15

Post by kat_rebelo »

oblib wrote: post #3

I posted some comments about ChatGTP in a local FB group and there was a pretty large percent of folks who responded here that think it's just an awful thing that's going to lead to the downfall of civilization. I tried to offer that it is pretty cool, but it's just software that basically presents search engine results in a different manner along with a few other tricks, but it's not "HAL". I live in a very red and…

i'm not a red state / far right / pro-trump in any sense of the word. however, i don't think it is very unreasonable to extrapolate bit and see the potential for societal harm.

over the past three years the entire world was impacted by a dire health crisis where misinformation played a large role in distorting public perception. this has direct impacts on public health (people not wearing masks, refusing vaccines) and has spillover effect into other parts of people's lives (political polarization around said issues).

what you see as a pretty cool toy could also easily be abused as a giant round the clock fake news generator. it doesn't matter if the text is true or even makes any sense... an alarming amount of people will take anything they read as fact without investigating the sources. this can be done as is with chatgpt right now. it has obscenity filters sure, but fake news is trying to pass as legitimate reporting, so it will probably be framed in a tone that escapes the obvious filters they have.

then consider the implications for robotexting, phishing, automated bots that pretend to be you to customer service chats, social media bots, messaging app scammers. all of these things are currently problems that can cause harm both personal and societal... and chatgpt will make it easier and cheaper to scale them up to new levels.

Re: ChatGPT Explained: A normie's guide to how it works

#16

Post by computomatic »

I get the sense that ChatGPT crosses a complexity threshold where there’s no good way to describe how it works that satisfies everybody, and that’s leading to cyclical stories of the form “everyone else describes it wrong, so here’s my take.”

As a heuristic, I see descriptions falling into simple buckets:

- stories that talk about tokens

- stories that don’t talk about tokens

Anything discussing technical details such as tokens never seems to really get around to the emergent properties that are the crux of ChatGPTs importance of society. It’s like talking about humanity by describing the function of cells. Accurate, but incomplete.

On the other hand, higher-level takes happily discuss the potential implications of the emergent behaviours but err on the side of attributing magic to the process.

I haven’t read much, to be fair, but I don’t see anyone tying those topics together very well.

Re: ChatGPT Explained: A normie's guide to how it works

#17

Post by not2b »

Nevermark wrote: post #11
imhoguy wrote: post #6

The biggest drawback of LLM is that it never answers with "I don't know" (unless it is some quote) and it just brings bullshit hallucinations which human has to reject as wrong. Thus it is mostly useless for anything serious. Personally I use it to beautify some text, but still have to do a bit of correction to fix b/s or missed context.

This seems like a great opportunity for some good old fashioned adversarial training. Post train one LLM to please another LLM, that rates the quality of the first model's responses and calls it on any bullshit! (And vice versa.)

I expect that this will be tried, and I worry about some negative consequences if it works well. It could be a way of generating very effective propaganda, that defeats the efforts of the opposing LLM to call bullshit.

On the other hand, diffusion models seem to have replaced GANs for image synthesis, so perhaps there's something I'm missing, or perhaps there's a way to combine both techniques.

Re: ChatGPT Explained: A normie's guide to how it works

#18

Post by jug »

imhoguy wrote: post #6

The biggest drawback of LLM is that it never answers with "I don't know" (unless it is some quote) and it just brings bullshit hallucinations which human has to reject as wrong. Thus it is mostly useless for anything serious. Personally I use it to beautify some text, but still have to do a bit of correction to fix b/s or missed context.

Bing AI often tells me that something is not known and when it hasn’t found any sources to confirm something. I think ChatGPT is worse off though.

Re: ChatGPT Explained: A normie's guide to how it works

#19

Post by icelancer »

imhoguy wrote: post #6

The biggest drawback of LLM is that it never answers with "I don't know" (unless it is some quote) and it just brings bullshit hallucinations which human has to reject as wrong. Thus it is mostly useless for anything serious. Personally I use it to beautify some text, but still have to do a bit of correction to fix b/s or missed context.

> The biggest drawback of LLM is that it never answers with "I don't know"

I see this a lot on social media, but it simply isn't true in my experience as someone who uses multiple APIs from OpenAI.

Re: ChatGPT Explained: A normie's guide to how it works

#20

Post by j_crick »

Nevermark wrote: post #4

I feel like as an intro aimed at "normies" it still manages to communicate in a more abstract and overthinky way than necessary. People often find it difficult to intuit examples from abstract descriptions. BUT, people are great at intuiting abstractions from concrete examples. You rarely need to explicitly mention abstractions, in informal talk. People's minds are always abstracting. > If I’m relating the collection…

> a generative model is a function that can take a structured collection of symbols as input and produce a related structured collection of symbols as output.

Yeah that’s exactly the way a nOrMiE would find easy to think about it. Duh.

The author probably should dish out that sentence on his grandparents and see how that would work before putting it on the internet and labeling it as “for normies”.

Post reply on HN