Poker has very high variance, you'd need several hundred thousand hands to confidently say who's better. Also, you probably want to precompute the GTO-optimal play for benchmarking purposes.
That was a whole half a decade ago, but back then deep learning AIs were defeated very badly by handcrafted scripts. Even the best bot in the neural net category was actual a symbolic script/neural net hybrid.
This is a good way to benchmark models. We [the SWE-bench team] took the meta-version of this and implemented it as a new benchmark called CodeClash -
We have agents implement agents that play games against each other- so Claude isn't playing against GPT, but an agent written by Claude plays poker against an agent written by GPT, and this really tough task leads to very interesting findings on AI for coding.
My personal threshold for AGI is when an AI can 'sit down' - it doesn't need to have robotic hands, but it needs to only use visual and audio inputs to make its moves - and complete a modern RPG or FPS single player game that it hasn't pre-trained on (it can train on older games).
It could have hands that feel but no vision, I think they were getting at that they thought embodiment and playing games in the modality of humans, without thousands of hours of play to reach competency, would be an important milestone.
If AI can program, why does it matter if it can play Chess using CoT when it can program a Chess Engine instead? This applies to other domains as well.
They should be allowed to! In fact i think better benchmark would be to invent new games and test the models ability to allocate compute to minmax/alphazero new games in compute constraints
It is a program. I need it to get task X done and I don't care how, whether it is strictly through CoT or with tools. There is no such thing as cheating in real work and no reason to handicap it. Just test the limits of what it can do with whatever means possible.
Trying to solve everything with CoT alone without utilising tools seems futile.
A lot of the insights of math come from knowing how to do things efficiently. That’s why the tests are timed. I don’t know, this is pretty basic pedagogy that you are choosing to grief.
> If AI can program, why does it matter if it can play Chess using CoT when it can program a Chess Engine instead?
Heh, we really did come full circle on this! When chatgpt launched in dec22 one of the first things that people noticed is that it sucked at math. Like basic math 12 + 35 would trip it up. Then people "discovered" tool use, and added a calculator. And everyone was like "well, that's cheating, of course it can use a calculator, but look it can't do the simple addition logic"... And now here we are :)
IMO there's an expectation for baseline intelligence. I don't expect an "AGI" model to beat Magnus Carlsen out of the box but it should be able to do basic grade school level arithmetic and play chess at a complete beginner level without resorting to external tools.
It can write a chess engine because it has read the code of a thousand of chess engines. This benchmark measures a different aspect of intelligence.
And as a poker player, I can say that this game is much more challenging for computers than chess, writing a program that can play poker really well and efficiently is an unsolved problem.
I'm not going to respond to everything but the key to my comment was "This applies to other domains as well." But people are limiting their imagination to the chess engine example given for chess. The tool or program (or even other neural networks that are available) can be literally anything for any task... Use your imagination.
Maybe we should just get rid of tedious benchmarks like chess altogether at this point that is leading people to think of how to limit AI as a way of keeping it a relevant benchmark rather than expanding on what is already there.
It’s not that bad. I’ve been using 3 Pro for some time now and I’m quite happy with how it works. Best paired with Opus and Codex, like most models, but it’s solid as a full-stack buddy.
Wow. I'm generally in the AI maximalist camp. But adding Werewolf feels dangerous to me. Anyone who's played knows lying, deceipt, and manipulation is often key to winning. We really want models climbing this benchmark?
negative benchmark isn't it? no sane lab is going to realease PR that states our newest model is best at lying, if anything the reverse may occur, if this catches on, they will make their model play werewolf badly and claim "alignment improvements, our model no longer lies as much in werewolf" but it lies more often in other domains
I'd really like to see them add a complex open world fully physicalized game like Star Citizen (assuming the game itself is stable) with a single primary goal like accumulating currency as a measure of general autonomy and a proxy for how the model might behave in the real world given access to a bipedal robot.
I believe that if a model can outperform humans in all board/card games, and can autonomously complete all video games, then AGI — or even ASI — has essentially been achieved. We’re still a long way from that.
As someone who's been playing dota for nearly 20 years now, it was fascinating to watch it play. Some of it's decision making process didn't seem logical in the short term, but would often be set ups for future plays, even though their observation window was fairly small. Even more impressively was the ai bot changed the meta of professional players, since tactics that arose out of its training ended up being more optimal.
I wish we got to the point where other ai bots were out there, but it's entirely understandable that you couldn't drive a complex game like Dota with LLMs, whereas you can with the ones the Game Arena has selected.
eamag | 12 hours ago
qsort | 12 hours ago
eamag | 11 hours ago
johndhi | 11 hours ago
tiahura | 12 hours ago
tux3 | 8 hours ago
That was a whole half a decade ago, but back then deep learning AIs were defeated very badly by handcrafted scripts. Even the best bot in the neural net category was actual a symbolic script/neural net hybrid.
tiahura | an hour ago
chaostheory | 11 hours ago
ofirpress | 11 hours ago
We have agents implement agents that play games against each other- so Claude isn't playing against GPT, but an agent written by Claude plays poker against an agent written by GPT, and this really tough task leads to very interesting findings on AI for coding.
https://codeclash.ai/
riku_iki | 11 hours ago
Instantnoodl | 11 hours ago
63stack | 10 hours ago
Are you going to share those with the class or?
RobRivera | 8 hours ago
?
cv5005 | 11 hours ago
bob1029 | 10 hours ago
anematode | 7 hours ago
Ultimately I think it's impossible to define AGI. Maybe "I know it when I see it"—except everyone sees it at a different point (evidently).
jamilton | 6 hours ago
10xDev | 11 hours ago
Davidzheng | 11 hours ago
simianwords | 10 hours ago
How you work without calculators is a proxy for real world competency.
10xDev | 10 hours ago
simianwords | 10 hours ago
10xDev | 10 hours ago
Trying to solve everything with CoT alone without utilising tools seems futile.
simianwords | 10 hours ago
10xDev | 8 hours ago
simianwords | 58 minutes ago
doctorpangloss | 10 hours ago
NitpickLawyer | 10 hours ago
Heh, we really did come full circle on this! When chatgpt launched in dec22 one of the first things that people noticed is that it sucked at math. Like basic math 12 + 35 would trip it up. Then people "discovered" tool use, and added a calculator. And everyone was like "well, that's cheating, of course it can use a calculator, but look it can't do the simple addition logic"... And now here we are :)
paxys | 9 hours ago
RivieraKid | 9 hours ago
And as a poker player, I can say that this game is much more challenging for computers than chess, writing a program that can play poker really well and efficiently is an unsolved problem.
10xDev | 8 hours ago
It doesn't even need to be one tool but a series of tools.
marksimi | 4 hours ago
CooCooCaCha | 9 hours ago
Chess engines don’t grow on trees, they’re built by intelligent systems that can think, namely human brains.
Supposedly we want to build machines that can also think, not just regurgitate things created by human brains. That’s why testing CoT is important.
It’s not actually about chess, it’s about thinking and intelligence.
10xDev | 8 hours ago
Maybe we should just get rid of tedious benchmarks like chess altogether at this point that is leading people to think of how to limit AI as a way of keeping it a relevant benchmark rather than expanding on what is already there.
simianwords | 11 hours ago
goniszewski | 10 hours ago
CuriouslyC | 9 hours ago
bennyfreshness | 11 hours ago
bilekas | 10 hours ago
AI already has a very creative imagination for role play so this just adds extra to their arsenal.
PunchyHamster | 10 hours ago
rustyhancock | 9 hours ago
Bizarre.
minihat | 6 hours ago
Rastonbury | 2 hours ago
ZeroCool2u | 10 hours ago
PunchyHamster | 10 hours ago
iNic | 8 hours ago
mclau153 | 8 hours ago
kenforthewin | 7 hours ago
https://kenforthewin.github.io/blog/posts/nethack-agent/
mohsen1 | 6 hours ago
https://mafia-arena.com
Gemini is consistently winning against top models
deyiao | 4 hours ago
jjcm | an hour ago
As someone who's been playing dota for nearly 20 years now, it was fascinating to watch it play. Some of it's decision making process didn't seem logical in the short term, but would often be set ups for future plays, even though their observation window was fairly small. Even more impressively was the ai bot changed the meta of professional players, since tactics that arose out of its training ended up being more optimal.
I wish we got to the point where other ai bots were out there, but it's entirely understandable that you couldn't drive a complex game like Dota with LLMs, whereas you can with the ones the Game Arena has selected.