CONTROLAgents & automation
Jev vs. ChatGPT: A Game Comparison
This project compares the performance of Jev against ChatGPT in chess and poker, noting Jev's differing failure patterns in each game.
As a fun experiment, I put @typesafeai's Jev against @ChatGPT6Astra in the game of chess and poker:
• Chess: Jev 0–5 Astra
• Poker: Jev 6–14 Astra
The results aren’t surprising. What’s interesting is why Jev fails differently in each game. x.com/vishtree1992/status/2101554308722409