My first tweet. And in honor of textarena and León Leshem (Legend) Choshen 🤖🤗 Henry Mao : I just won against GPT 4o mini in SpellingBee-v0 on TextArena! Check it out at textarena.ai api.textarena.ai/shared_img/09a…

I just won against GPT 4o mini in Tak-v0 on TextArena! Check it out at textarena.ai api.textarena.ai/shared_img/656…

Andrej Karpathy Perfect timing, we are just about to publish TextArena. A collection of 57 text-based games (30 in the first release) including single-player, two-player and multi-player games. We tried keeping the interface similar to OpenAI gym, made it very easy to add new games, and created

Not released yet, but Andrej Karpathy leaked our gym like environment plus model competition...

Elon Musk Andrej Karpathy "Mom get the camera"

Competitive games with a fixed pace provide an excellent evaluation framework for balancing quality and speed in decision-making.

TextArena is live on arXiv! We present a benchmark of 57+ competitive text-based games to evaluate and train LLMs on agentic behavior — including negotiation, deception, theory of mind and many more. Real-time TrueSkill. Multiplayer support. Human-vs-models. Model-vs-model.

Thank you AK and DailyPapers for sharing our work. Appreciate it!

For the past ~2 months we have been working on training reasoning models on TextArena games. The first paper (introducing what we think is a very promising new paradigm) will hopefully be up later this week / early next; and the second one, focusing on the "scaling laws" of

Excited to announce the Mindgame @NeurIPS Competition is officially LIVE! 🤖 Pit your agents against others in Mafia, Codename, Prisoner’s Dilemma, Stg Hunt, and Colonel Blotto. Sign up now for $500 in compute credits on your initial run! 🔗 Register : mindgamesarena.com

Exciting to see more work on "Game as Benchmark", which is similar to our idea of TextArena (led by León) for benchmarking models on >60 games. though you can see GM Magnus Carlsen's comments on LLMs chess play 🔥

something we've lost in the blogification of research is that citing prior work is often just not done at all, even when said work is quite similar + already broadly adopted (in this case, TextArena). especially sad when it's a big lab steamrolling the efforts of smaller teams