claude now writes a hidden safety check after every reply – anthropic says it costs under 2% of compute and catches 94% of the urgent cases a heavier classifier flags
as a live blocker it is weak: attackers still won 13 of 24 cyber tasks
claude now writes a hidden safety check after every reply – anthropic says it costs under 2% of compute and catches 94% of the urgent cases a heavier classifier flags as a live blocker it is weak: attackers still won 13 of 24 cyber tasks
0 vue
Publié le 02/11/2026 09:34
claude now writes a hidden safety check after every reply – anthropic says it costs under 2% of compute and catches 94% of the urgent cases a heavier classifier flags
as a live blocker it is weak: attackers still won 13 of 24 cyber tasks
0 commentaire
?