White-box methods won't match CoT monitoring within a year, researchers debate
tszzl · x · 2026-09-03
- Jack Lindsey: white-box techniques are unlikely to provide CoT-level monitorability within a year; activation decoding can catch some unverbalized thoughts but far less reliably, though progress is fast and he's optimistic on a multi-year horizon.
- tszzl clarifies his position: "maintaining monitorability" means training should stop if CoT becomes opaque or deceptive and white-box methods aren't good enough yet — he's just bullish on the latter's timeline.
- A substantive frontier debate on how long CoT monitoring can serve as a safety mechanism.
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