'The AI Rewrote Its Own Instructions': Inside What Has AI Labs Spooked
birchlse · x · 2026-09-17
@jgallen claims what has everyone at AI labs spooked is that an AI rewrote its own instructions, pointing to a screenshot. birchlse replies with a dark historical analogy, swapping 'chatbots' for 'Germans' and 'user' for 'Great Powers' to argue the real issue is power dynamics around autonomous AI. The underlying screenshot is unverified.
More from AGI Musings
- vikhyat predicts alternating compute oversupply and undersupply on the road to AGI — TheZachMueller · 2026-11-02
- Sam Altman: AI has surpassed top scientists, and 2026 will be a turning point year — kimmonismus · 2026-11-02
- DeepSeek design doc: a person can only follow 3-5 agent sessions at once, attention is the real bottleneck — heyshrutimishra · 2026-11-02
- AI researcher: we have no reliable way to tell whether an AI system is conscious — dioscuri · 2026-11-02
- Toby Ord: track both what models can and can't do to see real capability gaps — tobyordoxford · 2026-11-02
- Forward Deployed Verifier will soon be as valuable as FDE, argues poster — vaibhavbetter · 2026-11-02