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

481–490 of 659 posts

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

#481

Post by jes5199 »

kristianp wrote: post #104

I tried a problem I was looking at recently, to refactor a small rust crate to use one datatype instead of an enum, to help me understand the code better. I found o1-mini made a decent attempt, but couldn't provide error free code. o1-preview was able to provide code that compiled and passed all but the test that is expected to fail, given the change I asked it to make. This is the prompt I gave: simplify this rust l…

I cannot tell from reading what you wrote whether you think it did a good job or not

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

#482

Post by deegles »

I was thinking about what "actual" AI would be for me and it would be something that could answer questions like "tell me every time Nicolas Cage has blinked while on camera in one of his movies".

Sure, that is a contrived question, but I expect an "AI" to be capable pf obtaining every movie, watching them frame-by-frame, and getting an accurate count. All in a few seconds.

Current models (any LLM) cannot do that and I do not see a path for them to ever do that at a reasonable cost.

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

#483

Post by jes5199 »

nbzso wrote: post #457

Working in tech for over 30 years. This is the first time when I don't see proposed technology as a valuable tool. Especially LLM's. Vastly overhyped, driven by pure greed and speculative narratives, limited implementation and high energy cost. Non-transparent. Errors marketed as a hallucination.

this is exactly what i said about the iphone

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

#484

Post by bgun »

deegles wrote: post #482

I was thinking about what "actual" AI would be for me and it would be something that could answer questions like "tell me every time Nicolas Cage has blinked while on camera in one of his movies". Sure, that is a contrived question, but I expect an "AI" to be capable pf obtaining every movie, watching them frame-by-frame, and getting an accurate count. All in a few seconds. Current models (any LLM) cannot do that and…

I agree. My example for something “AI” should be able to do is to create a CAD model for the Empire State Building or the Parthenon based on known facts and photos.

I don’t think these are “moving the goalposts” examples, they are things that an actual intelligence capable of passing a PhD physics exam should be able to do.

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

#485

Post by Spivak »

ActionHank wrote: post #461
bambax wrote: post #281

Near the end, the quote from OpenAI researcher Jason Wei seems damning to me: > Results on AIME and GPQA are really strong, but that doesn’t necessarily translate to something that a user can feel. Even as someone working in science, it’s not easy to find the slice of prompts where GPT-4o fails, o1 does well, and I can grade the answer. But when you do find such prompts, o1 feels totally magical. We all need to find…

The stupidest thing about ai and automation is that they are trying to target it at large corporations looking to cut down on jobs or 10x productivity when all anyone actually wants is a robot to do their laundry and dishes.

You're describing a dish-washer and washing-machine.

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

#486

Post by lanstin »

grey-area wrote: post #199
achow wrote: post #167

Earlier quoted context omitted.

What I'm not able to comprehend is why people are not seeing the answer as brilliant! Any ordinary mortal (like me) would have jumped to the conclusion that answer is "Father" and would have walked away patting on my back, without realising that I was biased by statistics. Whereas o1, at the very outset smelled out that it is a riddle - why would anyone out of blue ask such question. So, it started its chain of thoug…

The 'riddle': A woman and her son are in a car accident. The woman is sadly killed. The boy is rushed to hospital. When the doctor sees the boy he says "I can't operate on this child, he is my son". How is this possible? GPT Answer: The doctor is the boy's mother Real Answer: Boy = Son, Woman = Mother (and her son), Doctor = Father (he says...he is my son) This is not in fact a riddle (though presented as one) and th…

"There are four lights"- GPT will not pass that test as is. I have done a bunch of homework with Claude's help and so far this preview model has much nicer formatting but much the same limits of understanding the maths.

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

#487

Post by cjonas »

ryoshu wrote: post #385
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…

1000% this. LLMs can't say "I don't know" because they don't actually think. I can coach a junior to get better. LLMs will just act like they know what they are doing and give the wrong results to people who aren't practitioners. Good on OAI calling their model Strawberry because of Internet trolls. Reactive vs proactive.

The difference is a junior cost 30-100$/hr and will take 2 days to complete the task. The LLM will do it in 20 seconds and cost 3c

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

#488

Post by grey-area »

kristianp wrote: post #311
roomey wrote: post #223

Earlier quoted context omitted.

Why couldn't the doctor be the boys mother? There is no indication of the sex of the doctor, and families that consist of two mothers do actually exist and probably doesn't even count as that unusual.

So the riddle could have two answers: mother or father? Usually riddles have only one definitive answer. There's nothing in the wording of the riddle that excludes the doctor being the father.

This particular riddle the answer is the doctor is the father.

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

#489

Post by mdaniel »

zurfer wrote: post #417
biscuit1v9 wrote: post #257

Earlier quoted context omitted.

Link to conversation 1 and 2 doesn't work. Update it please!

sorry for that. I just learned that my team account does not allow me to share conversations publicly. Pasting them here for reference * Conversation 1 let's play tic tac toe. you need to play optimally ChatGPT Sure, I'd be happy to play tic-tac-toe with you! Let's set up the game. We'll use a grid with positions numbered 1 through 9: markdown 1 | 2 | 3 --------- 4 | 5 | 6 --------- 7 | 8 | 9 Would you like to be X o…

  Sure! Here's the 3x5 Tic Tac Toe board. Each cell is numbered for easy reference:

    diff
I'm presuming that copy paste ate the ``` part and I found it interesting that in the first chat it correctly(?) used a markdown code fence but in the 2nd chat it chose to use diff syntax for its table. I suppose it rendered the text in a monospace font?

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

#490

Post by grey-area »

Jensson wrote: post #472
TeMPOraL wrote: post #392

Earlier quoted context omitted.

Yup. The models fail on gotcha questions asked without warning, especially when evaluated on the first snap answer. Much like approximately all humans.

> especially when evaluated on the first snap answer The whole point of o1 is that it wasn't "the first snap answer", it wrote half a page internally before giving the same wrong answer.

Is that really its internal 'chain of thought' or is it a post-hoc justification generated afterward? Do LLMs have a chain of thought like this at all or are they just convincing at mimicking what a human might say if asked for a justification for an opinion?
Post reply on HN