model safety

July 10, 202511.2k0
EU’s AI Transparency Code: What Tech Giants Will Dislike
The European Commission has published a voluntary code of practice under the landmark EU ...

June 10, 20254.5k0
Misalignment on a Budget: Finetuning and Steering Vectors
Published on June 8, 2025 3:28 PM GMT TL;DR We reproduce emergent misalignment (Betley ...

June 5, 20253.3k0
AI Moratorium Fails: Amodei’s Push for Transparency Standards
By expanding on technical challenges, regulatory comparisons, and expert perspectives, we explore why a ...