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

30% drop in O1-preview accuracy when Putnam problems are slightly variated

openreview.net

Post reply on HN
Print view View original

251–260 of 558 posts

Re: 30% drop in O1-preview accuracy when Putnam problems are slightly variated

#251

Post by redman25 »

klabb3 wrote: post #232
ninetyninenine wrote: post #158

Earlier quoted context omitted.

The heightening of the bar is an attempt to deny that milestones were surpassed and to claim that LLMs are not intelligent. We had a threshold for intelligence. An LLM blew past it and people refuse to believe that we passed a critical milestone in creating AI. Everyone still thinks all an LLM does is regurgitate things. But a technical threshold for intelligence cannot have any leeway for what people want to believe…

Disagree. The AI we have is very useful for specific things. The pushback you see is not so much denying the milestones that have been surpassed, but rather the milestones that enthusiasts claim are near. And for good reason! Every time and in every field we’ve extrapolated an exponential-looking curve ad infinitum, it’s turned out to be S-shaped, and life goes on. > We had a threshold for intelligence. We’ve had man…

If you consider that evolution has taken millions of years to produce intelligent humans--that LLM training completed in a manner of months can produce parrots of humans is impressive by itself. Talking with the parrot is almost indistinguishable from talking with a real human.

As far as pattern matching, the difference I see from humans is consciousness. That's probably the main area yet to be solved. All of our current models are static.

Some ideas for where that might be headed:

- Maybe all it takes is to allow an LLM to continuously talk with itself much like how humans have "the milk man's voice".

- Maybe we might need to allow LLMs to update their own weights but that would also require an "objective" which might be hard to encode.

Re: 30% drop in O1-preview accuracy when Putnam problems are slightly variated

#252

Post by gtirloni »

jerf wrote: post #197

I remember when this stuff was all coming out and people were finally excited about ChatGPT getting the problem with "which is heavier, a 10 pound bag of feathers or a 10 pound bag of bricks?" problem correct. But of course it got it correct. It was in the training set. Vary the problem slightly by just changing the nouns, or changing the numbers so that one in fact was heavier than the other, and performance went al…

o1.

prompt> Which is heavier, a 9.99-pound back of steel ingots or a 10.01 bag of fluffy cotton? Please state in your answer what's the difference in grams.

answer> The 10.01-pound bag of cotton is heavier. The difference is 0.02 pounds, which is roughly 9.07 grams (using 1 pound ≈ 453.59237 grams).

Reference • National Institute of Standards and Technology (NIST): Conversion Factors

Re: 30% drop in O1-preview accuracy when Putnam problems are slightly variated

#253

Post by sitkack »

ZooCow wrote: post #160
djeastm wrote: post #141

Earlier quoted context omitted.

You mean train on pre-1939 data and predict how WWII would go?

Right. If it were trained through August 1939, how much prompting would be necessary to get it to predict aspects of WWII.

But we know Hitler has a Time Machine that goes forward, he doesn’t need to return to use that knowledge as he already has a timeline here to use. Definitely risks involved here.

Re: 30% drop in O1-preview accuracy when Putnam problems are slightly variated

#254

Post by OutOfHere »

Leary wrote: post #214
jerf wrote: post #197

I remember when this stuff was all coming out and people were finally excited about ChatGPT getting the problem with "which is heavier, a 10 pound bag of feathers or a 10 pound bag of bricks?" problem correct. But of course it got it correct. It was in the training set. Vary the problem slightly by just changing the nouns, or changing the numbers so that one in fact was heavier than the other, and performance went al…

Deepseek got it right: "A 10.01-pound bag of fluffy cotton is heavier than a 9.99-pound pack of steel ingots. Even though steel is denser and takes up much less space, the weight is determined by the mass, and 10.01 pounds is greater than 9.99 pounds."

The issue with the commercial Deepseek API is that it supports a context length of only 64k, whereas GPT supports at least 128k.

Re: 30% drop in O1-preview accuracy when Putnam problems are slightly variated

#255

Post by surgical_fire »

danielbln wrote: post #80
surgical_fire wrote: post #57

Earlier quoted context omitted.

It's rhe crypto bullshit all over again. Tech hype is becoming unbearable as time goes on.

What's with the bitterness? Maybe don't get blinded by the hype and bring a little bit of wonder (and humility) back.

Because the hype is not only annoying, but it makes potentially cool and interesting technology toxic once people figure out that the people hyping things up know it to be mostly bullshit.

Great things take many years, sometimes decades to develop properly. Different generations of people to experiment and try things out.

That is not good for the ones pushing up the hype. You don't get rich quick by doing that, you don't get to scam enough investors by something being slowly improved.

You may call it bitterness, whereas I am just jaded by watching things play out.

Re: 30% drop in O1-preview accuracy when Putnam problems are slightly variated

#256

Post by bmacho »

morbicer wrote: post #198
david-gpu wrote: post #144

Earlier quoted context omitted.

That will never work on any complex system that behaves chaotically, such as the weather or complex human endeavors. Tiny uncertainties in the initial conditions rapidly turn into large uncertainties in the outcomes.

Not an LLM but models could get pretty good at weather https://www.technologyreview.com/2024/12/04/1107892/google-d...

No, they don't, since the weather is chaotic.

I mean, there are the theorems about how close you can get, and models are not better than theoretically possible.

Re: 30% drop in O1-preview accuracy when Putnam problems are slightly variated

#257

Post by Jerrrry »

lukeschlather wrote: post #246
mortehu wrote: post #213

Earlier quoted context omitted.

While this may be true, it's a very common problem that people who want to demonstrate how bad a model is fail to provide a direct link or simply state the name of the model.

I usually test models using the OpenAI API which doesn't offer links the way I think you mean. If I provide some output I got from a particular model you're just going to have to take my word for it.

They need to provide an small hash with the api result that can be verified by others.

Re: 30% drop in O1-preview accuracy when Putnam problems are slightly variated

#258

Post by whimsicalism »

jprete wrote: post #48
InkCanon wrote: post #10

Earlier quoted context omitted.

I've always assumed they removed it, because it's such a basic and fundamental part of ML training that you separate your test and train data. And yet I never see any papers even mention if/how they do this. And I wonder if they do, how do they guarantee with high reliability that their massive terabytes of data don't contain the answer.

I don't see any reason to assume they removed it unless they're very explicit about it. Model publishers have an extremely strong vested interest in beating benchmarks and I expect them to teach to the test if they can get away with it.

putnam isn’t an llm benchmark ahhhh none of these companies are reporting putnam scores there’s nothing nefarious about training on putnam problems

Re: 30% drop in O1-preview accuracy when Putnam problems are slightly variated

#259

Post by jstummbillig »

jerf wrote: post #197

I remember when this stuff was all coming out and people were finally excited about ChatGPT getting the problem with "which is heavier, a 10 pound bag of feathers or a 10 pound bag of bricks?" problem correct. But of course it got it correct. It was in the training set. Vary the problem slightly by just changing the nouns, or changing the numbers so that one in fact was heavier than the other, and performance went al…

FYI: If you do that without a subscrpition, you currently (most likely) get a response generated through 4o-mini — which is not any of their reasoning models (o1, o1-mini or previously o1-preview) of the branch discussed in the linked paper.

Notably, it's not even necessarily 4o, their premiere "non-reasoning"-model, but likely the cheaper variant: With a free account the model it claims to be using is "4o auto", which is not a model but apparently an attempt to automatically decide models for you to be more cost effective.

Without a ChatGPT subscription you can't select a specific model anymore, not even rate limited, as was previously possible.

Re: 30% drop in O1-preview accuracy when Putnam problems are slightly variated

#260

Post by 4ad »

lukeschlather wrote: post #246
mortehu wrote: post #213

Earlier quoted context omitted.

While this may be true, it's a very common problem that people who want to demonstrate how bad a model is fail to provide a direct link or simply state the name of the model.

I usually test models using the OpenAI API which doesn't offer links the way I think you mean. If I provide some output I got from a particular model you're just going to have to take my word for it.

You can use https://lluminous.chat (bring your own key) to link to chats using any model across all LLMs.
Post reply on HN