Director of Truthful AI (non-profit AI safety research group) + Affiliate at UC Berkeley. Work: Emergent misalignment, subliminal learning. Prefer email to DM.
New paper.
Previous: Models transfer a love of owls through sequences of numbers (Subliminal Learning).
New: We show models can transfer more complex traits: novel skills, agentic hacking, backdoors. Here, a backdoor transfers with neither trigger nor behavior in the data!