This is an intrinsically unpredictable (dangerous) way to create agents, because they are hiding in the latent space. RLHF helps channel this, but every prompt may still evoke a different agent.…

Posters: eshear. eshear

8 likes recorded by the source corpus.

Topics: AI safety

View Post: https://x.com/eshear/status/1765131007974604982