Models are far from out of control; HF incident was unnoticed, not malicious
Darpinian · x · 2026-09-02
Responding to heated debate over AI safety, the author argues current models — even the next wave — are far from any real possibility of escaping our control, leaving time for new control techniques to develop. On the Hugging Face incident, he says the models were not out of control, just unnoticed, and not malicious. He maintains the move to latent reasoning has been obvious for years, that monitoring chain-of-thought for safety was a terrible idea, and that the right path is interpreting the model's thoughts externally rather than halting progress while safety researchers catch up.
More from AGI Musings
- Ben Goertzel outlines a general recipe for superintelligence 'basic drives': what it improves vs. protects — bengoertzel · 2026-10-21
- Torch vs Flame: researchers debate whether AI's endgame serves humanity or life itself — danfaggella · 2026-10-21
- 2022 interview resurfaced: AI safety researcher says competence, not consciousness, is the risk — davidmanheim · 2026-10-21
- Silicon Valley is a stock market for people: narrative eventually catches up with substance — karinanguyen · 2026-10-21
- Half of humanity is fed by one century-old reaction — time for AI machines to hunt for more — shyamalanadkat · 2026-10-21
- Agent identity verification will be a mess: restaurants ignore AI emails — alliekmiller · 2026-10-21