AI Dynamics

Global AI News Aggregator

About

Llama-2 Improves Game Performance Through Adversarial Self-Play

This is worth noting: it appears to be the first evidence that LLMs can improve performance at a task through self-play. In this case, Llama-2 7B was able to greatly improve its ability to play the game of Adversarial Taboo by training through adversarial competition with itself

→ View original post on X — @emollick