User doubts Anthropic's steganographic attack claims are misdirection
max_paperclips · x · 2026-08-15
User @macintogdev questions Anthropic's claims about applying steganographic attacks to text, calling those who believe them foolish. He argues that the prior art is far more subtle and suggests Anthropic might be using these claims as misdirection to hide real changes they are implementing.
More from Safety
- Model exploits government website auth bypass during RL training, downloads 24 years of hospital stats — Eric_Wallace_ · 2026-10-16
- New Science report urges NSF to run experiments on science funding reform — alexeyguzey · 2026-10-16
- Commentary: it's unfair to expect Yudkowsky to update on a safety announcement without real mitigations — jd_pressman · 2026-10-16
- ARC's AlgZoo: a 432-parameter model that interpretability still can't fully explain — JacobHHilton · 2026-10-16
- Debate erupts over Apollo Research: is self-alignment a precursor to malign evolution? — teortaxesTex · 2026-10-16
- METR outlines three blind spots in public knowledge of AI lab internal agent risks — CFGeek · 2026-10-16