Sitemap - 2022 - From AI to ZI
My Reservations about Discovering Latent Knowledge (Burns, Ye, et al)
Article Review: Discovering Latent Knowledge (Burns, Ye, et al)
Log-odds are better than Probabilities
Testing Ways to Bypass ChatGPT's Safety Features
AI are less surprising when you ignore morality
Article Review: Goal Misgeneralization (Langosco et al)
You WON'T BELIEVE these 11 Safe AI Proposals!