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

Notes on OpenAI's new o1 chain-of-thought models

simonwillison.net

Post reply on HN
Print view View original

651–659 of 659 posts

Re: Notes on OpenAI's new o1 chain-of-thought models

#651

Post by KoolKat23 »

dartos wrote: post #647
KoolKat23 wrote: post #639

Earlier quoted context omitted.

No I'm not saying they must work the same way. I'm saying it's evidence there is a more efficient way as they both solve the same problem and one is more efficient (in truth both are more efficient in different areas). At an abstract level they can be doing the same thing. What does a simulator do? Think a little further yes, currently it's a brand new model each time but why will it be this way forever? Its an engin…

So you’re just abstracting everything to the point where everything is a “something solver” and if two things can solve the same something, one must be a better version of the other? Abstracting everything to the point of meaninglessness isn’t a worthwhile exercise.

No, that's a stretch and even from that how do you get to that conclusion? I think you're clearly trying to brush off my comment.

I assume you're of the opinion humans are special.

Re: Notes on OpenAI's new o1 chain-of-thought models

#652

Post by mercer »

williamdclt wrote: post #164
MPSimmons wrote: post #106

Earlier quoted context omitted.

The failure is in how you're using it. I don't mean this as a personal attack, but more to shed light on what's happening. A lot of people use LLMs as a search engine. It makes sense - it's basically a lossy compressed database of everything its ever read, and it generates output that is statistically likely - varying degrees of likeliness depending on the temperature, as well as how many times the particular weights…

> Treat it as a naive but intelligent intern That’s the problem: it’s a _terrible_ intern. A good intern will ask clarifying questions, tell me “I don’t know” or “I’m not sure I did it right”. LLMs do none of that, they will take whatever you ask and give a reasonable-sounding output that might be anything between brilliant and nonsense. With an intern, I don’t need to measure how good my prompting is, we’ll usually…

Can I have some of those sorts of interns?

Re: Notes on OpenAI's new o1 chain-of-thought models

#653

Post by flanked-evergl »

simonw wrote: post #616
flanked-evergl wrote: post #612

Earlier quoted context omitted.

One example: https://www.theverge.com/2024/3/28/24114664/microsoft-safety... > Three features: Prompt Shields, which blocks prompt injections or malicious prompts from external documents that instruct models to go against their training; Groundedness Detection, which finds and blocks hallucinations; and safety evaluations, which assess model vulnerabilities, are now available in preview on Azure AI.

That wasn’t OpenAI making those claims, it was Microsoft Azure.

I never said it was OpenAI that made the claims.

Re: Notes on OpenAI's new o1 chain-of-thought models

#654

Post by pedrosorio »

TeMPOraL wrote: post #469
kasdfasH wrote: post #332

Earlier quoted context omitted.

The original riddle is of course: "A father and his son are in a car accident [...] When the boy is in hospital, the surgeon says: This is my child, I cannot operate on him". In the original riddle the answer is that the surgeon is female and the boy's mother. The riddle was supposed to point out gender stereotypes. So, as usual, ChatGPT fails to answer the modified riddle and gives the plagiarized stock answer and e…

> So, as usual, ChatGPT fails to answer the modified riddle and gives the plagiarized stock answer and explanation to the original one. No intelligence here. Or, fails in the same way any human would, when giving a snap answer to a riddle told to them on the fly - typically, a person would recognize a familiar riddle half of the first sentence in, and stop listening carefully, not expecting the other party to give th…

> Or, fails in the same way any human would, when giving a snap answer to a riddle told to them on the fly

The point of o1 is that it's good at reasoning because it's not purely operating in the "giving a snap answer on the fly" mode, unlike the previous models released by OpenAI.

Re: Notes on OpenAI's new o1 chain-of-thought models

#655

Post by Closi »

williamdclt wrote: post #164
MPSimmons wrote: post #106

Earlier quoted context omitted.

The failure is in how you're using it. I don't mean this as a personal attack, but more to shed light on what's happening. A lot of people use LLMs as a search engine. It makes sense - it's basically a lossy compressed database of everything its ever read, and it generates output that is statistically likely - varying degrees of likeliness depending on the temperature, as well as how many times the particular weights…

> Treat it as a naive but intelligent intern That’s the problem: it’s a _terrible_ intern. A good intern will ask clarifying questions, tell me “I don’t know” or “I’m not sure I did it right”. LLMs do none of that, they will take whatever you ask and give a reasonable-sounding output that might be anything between brilliant and nonsense. With an intern, I don’t need to measure how good my prompting is, we’ll usually…

> With an intern, I don’t need to measure how good my prompting is, we’ll usually interact to arrive to a common understanding.

With interns you absolutely do need to worry about how good your prompting is! You need to give them specific requirements, training, documentation, give them full access to the code base... 'prompting' an intern is called 'management'.

Re: Notes on OpenAI's new o1 chain-of-thought models

#656

Post by ddrdrck_ »

Closi wrote: post #655
williamdclt wrote: post #164

Earlier quoted context omitted.

> Treat it as a naive but intelligent intern That’s the problem: it’s a _terrible_ intern. A good intern will ask clarifying questions, tell me “I don’t know” or “I’m not sure I did it right”. LLMs do none of that, they will take whatever you ask and give a reasonable-sounding output that might be anything between brilliant and nonsense. With an intern, I don’t need to measure how good my prompting is, we’ll usually…

> With an intern, I don’t need to measure how good my prompting is, we’ll usually interact to arrive to a common understanding. With interns you absolutely do need to worry about how good your prompting is! You need to give them specific requirements, training, documentation, give them full access to the code base... 'prompting' an intern is called 'management'.

This might be the best definition I will come across of what it means to be an "IT project manager".

Re: Notes on OpenAI's new o1 chain-of-thought models

#657

Post by throwaway4aday »

HarHarVeryFunny wrote: post #646
idiotsecant wrote: post #644

Earlier quoted context omitted.

Its entirely possible to have an AGI language model that is periodically retrained as slang, vernacular, and semantic embeddings shift in their meaning. I have little doubt that something very much like an LLM (a machine that turns high dimensional intent into words) will form an AGIs 'language center' at some point.

Yes, an LLM can be periodically retrained, which is what is being done today, but a human level AGI needs to be able to learn continuously. If we're trying something new and make a mistake, then we need to seamlessly learn from the mistake and continue - explore the problem and learn from successes and failures. It wouldn't be much use if your "AGI" intern stopped at it's first mistake and said "I'll be back in 6 mon…

I don't think there's a single way that we learn things, there's too much variety in how, when and why things are committed to memory and still more of a difference with things that actually update our thinking process or world model. We forget the overwhelming majority of sense perceptions immediately and even when we are intentionally trying to learn something we will fail to recall it even a few seconds after we see it. Even when we succeed in short term recall the thing we have "learnt" may be gone the next day or we may only recall it correctly some small number of times out of many attempts. Contrary to that some things are immediately and permanently ingrained in our minds if they are extremely impactful in some way or sometimes for no apparent reason at all. It's too deep of a topic to go into but all this is to say that it isn't so simple as to say that continued pretraining of an LLM is completely dissimilar to how humans learn, in fact the question and answer style of fine tuning that is so widely used to add new knowledge or steer a model to respond in a certain way is extremely similar to how humans learn e.g. quizzing or testing with immediate feedback and repeating the process with many samples that vary their wording while still pertaining to the same information is one of the best ways for people to memorize information.

Re: Notes on OpenAI's new o1 chain-of-thought models

#658

Post by poochkoishi728 »

MadSudaca wrote: post #415
poochkoishi728 wrote: post #245

Earlier quoted context omitted.

{0, -1, 1}. Divide (in order): 0/-1 -> 0/1 -> 0. Add: 0 - 1 + 1 = 0

also {-1, 1, 1}

Seems not to work as division yields -1 (-1/1/1) and adding them yields +1 (-1+1+1).

Re: Notes on OpenAI's new o1 chain-of-thought models

#659

Post by knicholes »

cma wrote: post #47
knicholes wrote: post #32

Earlier quoted context omitted.

I dunno man. I just spent a couple hours trying to get it to write functioning code to read from my RTSP stream, detect if my kid is playing piano, and send the result to HomeAssistant. It did not succeed.

How many hours without it?

That remains to yet be seen, as I kept insisting that an LLM should be able to write this in its entirety with success with "just one more prompt change".
Post reply on HN