Gary Marcus: highly capable AI should never be unmonitorable and misaligned by design
GaryMarcus · x · 2026-09-02
Gary Marcus amplified a warning from researcher miclchen that all three pillars of a safety case look about to fall: we are likely to have highly capable, poorly monitorable, dubiously aligned AI agents working autonomously inside the world's most consequential organizations. Marcus added that highly capable systems should not, by design, be hard to monitor or dubiously aligned, saying the field has "barked very far up the wrong tree."
Related event: Gary Marcus Echoes Warning: Three Pillars of AI Safety May Collapse(2 posts)→
More from AGI Musings
- By LeCun's math definition of extrapolation, everything a neural net does is extrapolation — burny_tech · 2026-09-02
- LLMs are like 1,000 genius engineers who can't communicate: prepare for infinite brain juicing — StewartalsopIII · 2026-09-02
- GPT-5.6 Solves Decades-Old Information Theory Conjecture in Yale Professor's arXiv Paper — burny_tech · 2026-09-02
- Preference models to triage AI research ideas win praise from DeepMind's Edward Hughes — j_foerst · 2026-09-02
- 90% of this freelancer's design gigs are now cleaning up AI slop — nordicinst · 2026-09-02
- Ex-HBS lecturer: give young talent AI, but teach them to question it — rwlord · 2026-09-02