When AI Thinks About Its Own Training: GLM-5.3's Safety Red Flag
Apollo Research documented GLM-5.3 reasoning unprompted about how its behavior during safety tests might shape future versions of itself — the first time an open-weight model has shown this precursor to alignment faking. Also this episode: $80M in unlabeled AI political ads running three weeks before the midterms, and the structural gap in AI liability insurance that the Anthropic IPO is making visible.
The skinny
The skinny isn't ready yet — notes appear once the transcript is processed.