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

When AI Benchmarks Plateau: A Systematic Study of Benchmark Saturation

arxiv.org

Post reply on HN
Print view View original

131–139 of 139 posts

Re: When AI Benchmarks Plateau: A Systematic Study of Benchmark Saturation

#131

Post by gertlabs »

erikwiffin wrote: post #52
gertlabs wrote: post #16

I started thinking about this back after the Llama 4 release, and since then our team has put a lot of thought into designing evaluations that don't saturate, are resistant to contamination, and can scale. What has worked best for us is using multi-agent environments with open-ended cooperative or competitive goals. Mostly designed as multiplayer games. The results tend to align with our experience for coding better…

I've developed a benchmark that I think should be resistant to saturation, is easily verifiable, and anecdotally correlates with desirable behavior (ability to not get confused while generating text with state). I think it's interesting, I think other people would find it useful, but I don't want to spend a bunch of money running it against all the frontier models. What's the best way to reach out to labs like yours…

SlimeBallBench? Looks cool, love the implementation! You would most likely need a LOT of environments like these if your goal was selling them to labs

Re: When AI Benchmarks Plateau: A Systematic Study of Benchmark Saturation

#132

Post by scotty79 »

ACCount37 wrote: post #87
astro1234 wrote: post #54

Earlier quoted context omitted.

Yea this may explain part of it or all of it, it’s likely a case by case kind of thing. Also to respond to the parent comment: benchmarks have a variety of difficulty levels. Humanity’s Last Exam, though now hitting the beginning of a saturation phase with Fable, was long unsaturated while other benchmarks saturated awhile ago. So that’s what I meant by Epoch capability index: using IRT models this effect so that you…

Saturation is mostly just selection effects in play. Throw out the "90% easiest" of tasks, and what remains is a jagged ladder of high difficulty outliers. Hard to climb, and hard to measure the climb - because you have less effective data points and the datapoints themselves are less linear, while you're still being subject to the measurement noise. Not having the mislabeled tasks would reduce the saturation, but it…

You almost can't give a correct answer to a task with expected wrong answer unless you know it expects wrong answer. ... maybe on a yes/no question by chance. But as you become more knowledgeable, the probability that you give wrong but expected answer reduces.

If a benchmark saturates to 100% it's very likely that answers leaked into the training data.

In college I had a funny exam. It was on C++. One question I had to answer incorrectly because there was a mistake in the question. So I gave two answers for it, one that answered the question as it was and the other that answered the question as I inferred it was intended to be. It was appreciated. I got a honorary mark above the top possible (I gave correct answers to all other questions). I wouldn't be surprised if across so many, so huge benchmarks, there were tasks with wrong questions or answers in the key, that some LLM answered in and expected manner in the same fashion.

Re: When AI Benchmarks Plateau: A Systematic Study of Benchmark Saturation

#133

Post by scotty79 »

freejazz wrote: post #42
logicchains wrote: post #13

Earlier quoted context omitted.

Talk about moving the goalposts. Pray tell, exactly what must an LLM do before you're willing to consider it AI? Be specific, otherwise you're just woo-mongering.

Everyone here is talking about LLMs, why bother calling them something else

I feel like LLMs refers to a model that for a given message responds with its own message.

And I feel like AI agents (powered by some LLM) are qualitatively something else.

Re: When AI Benchmarks Plateau: A Systematic Study of Benchmark Saturation

#134

Post by Yopolo »

827a wrote: post #115
Yopolo wrote: post #103

Earlier quoted context omitted.

"become more linear starting in Q4" We are not even close to what AI slowdown looks like. The whole business side of things are now building Agentic Layer for Business applications. All of this Agentic Layer needs to be build and its happening right now and still needs a little bit of time. Anthropic and co have the biggest and centralized reinforcement loop on the planet: Millions of people telling them what is good…

Your issue, I believe, is that you seem to believe capabilities are measured along one axis. This is natural to believe because it is representative of how the models have evolved up to this point, and thus it is also what many AGI-pilled people believe. Critically, you did not quote the most important part of my sentence: "useful progress will probably slow down and become more linear starting in Q4"; your omission…

No clue why you have to respond like this.

Feel free to be a dick to someone else.

Re: When AI Benchmarks Plateau: A Systematic Study of Benchmark Saturation

#135

Post by naasking »

DiscourseFan wrote: post #130
naasking wrote: post #127

Earlier quoted context omitted.

That's just vibes then. How is that supposed to be convincing?

Unless you are working for a competing firm or have a specific clause in your contract, you can literally just sign up for AI projects as a contractor and start contributing. You will see and understand everything after a few months. Nobody is hiding this knowledge really.

I use LLMs regularly for real work. I understand the current limitations, but you're talking about existing limitations that will never be overcome, because they cannot be overcome. I'm just asking for a couple of specific examples, and your evasions are increasingly suspicious.

Re: When AI Benchmarks Plateau: A Systematic Study of Benchmark Saturation

#136

Post by erikwiffin »

gertlabs wrote: post #131
erikwiffin wrote: post #52

Earlier quoted context omitted.

I've developed a benchmark that I think should be resistant to saturation, is easily verifiable, and anecdotally correlates with desirable behavior (ability to not get confused while generating text with state). I think it's interesting, I think other people would find it useful, but I don't want to spend a bunch of money running it against all the frontier models. What's the best way to reach out to labs like yours…

SlimeBallBench? Looks cool, love the implementation! You would most likely need a LOT of environments like these if your goal was selling them to labs

SlimeBallBench was not me, but it is cool! and at least partially what inspired me to build my own.

Mine is less fun, but hopefully more useful https://erikwiffin.github.io/memory-reasoning-eval/

Selling to labs is more than I'm looking for. I'm aiming for a couple hundred dollars so I don't have to finance a Fable vs Sol run out of my own pocket. It would be cool to have my benchmark be one of the ones referenced in a model card!

Re: When AI Benchmarks Plateau: A Systematic Study of Benchmark Saturation

#137

Post by DiscourseFan »

naasking wrote: post #135
DiscourseFan wrote: post #130

Earlier quoted context omitted.

Unless you are working for a competing firm or have a specific clause in your contract, you can literally just sign up for AI projects as a contractor and start contributing. You will see and understand everything after a few months. Nobody is hiding this knowledge really.

I use LLMs regularly for real work. I understand the current limitations, but you're talking about existing limitations that will never be overcome, because they cannot be overcome. I'm just asking for a couple of specific examples, and your evasions are increasingly suspicious.

If you are using them and you are aware of their limitations it’s very different from specifically testing them for training purposes. You’ll get a much clearer picture that way.

Re: When AI Benchmarks Plateau: A Systematic Study of Benchmark Saturation

#138

Post by freeone3000 »

slopinthebag wrote: post #126
freeone3000 wrote: post #116

Earlier quoted context omitted.

Because they’ve gotten good enough at lots of other things, and the RL keeps improving them, so enough RL should make them good enough at the focus areas.

I've gotten pretty strong in the gym, my bench has improved to two plates. I see no reason why it won't continue to improve until I can bench my house.

I think it’s a bit closer than that. You can bench two plates, and “good enough” is two plates on the bench and a three plate squat. LLMs haven’t started leg day.

Re: When AI Benchmarks Plateau: A Systematic Study of Benchmark Saturation

#139

Post by naasking »

DiscourseFan wrote: post #137
naasking wrote: post #135

Earlier quoted context omitted.

I use LLMs regularly for real work. I understand the current limitations, but you're talking about existing limitations that will never be overcome, because they cannot be overcome. I'm just asking for a couple of specific examples, and your evasions are increasingly suspicious.

If you are using them and you are aware of their limitations it’s very different from specifically testing them for training purposes. You’ll get a much clearer picture that way.

The continued vagueness suggests this isn't going anywhere, so I'll just conclude by saying that you've given nobody any real reason to believe this.
Post reply on HN