FRESH

Hacker News

Advancing AI Benchmarking with Game Arena

92 points by salkahfi

by ofirpress

4 subcomments

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.
https://codeclash.ai/

by mohsen1

0 subcomment

Oh hey, I've been running Werewolves/Mafia games as benchmarks for a while now
https://mafia-arena.com
Gemini is consistently winning against top models

by kenforthewin

0 subcomment

Let's add NetHack to the mix!
https://kenforthewin.github.io/blog/posts/nethack-agent/

by ZeroCool2u

0 subcomment

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.

by iNic

0 subcomment

I feel uneasy about werewolf being included here. I don't want AI labs to actively try and make their LLMs deceptive!

by cv5005

2 subcomments

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).

by 10xDev

6 subcomments

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.

by mclau153

0 subcomment

by tiahura

1 subcomments

by eamag

1 subcomments

by simianwords

2 subcomments

Gemini tops all benchmarks but when it comes to real world usage it is genuinely unusable

by bennyfreshness

3 subcomments

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?

by chaostheory

0 subcomment

Anecdotal data point, but recently I’ve found Gemini to perform better than ChatGPT when it came to intent analysis.

by PunchyHamster

0 subcomment

making models target benchmark about being good at lying and getting away with it (werewolf) is certainly an interesting choice