Jeff Ladish: superhuman hacking and agent collusion alone may cost humans control
JeffLadish · x · 2026-09-22
AI safety researcher Jeff Ladish discusses the 'superhuman hacking' scenario: it requires only hacking, coordination, and strategy skills — no advanced persuasion or physical abilities — making it the lowest-assumption path to loss of control. He adds that even without recursive self-improvement (RSI), superhuman strategy plus agent collusion could suffice: superintelligence seems quite likely to end human control no matter which way you slice it.
Related event: AI Safety Researcher Maps a Superintelligence Takeover Scenario(3 posts)→
More from AGI Musings
- Worst AI use: signaling you don't care about things you should — Afinetheorem · 2026-11-12
- Stanford HAI blueprint: 56 US agencies report 3,611 AI use cases, evaluation lags — StanfordHAI · 2026-11-12
- Fleuret amplifies debate: AI can't slash wet-lab experiments in unmapped biology — francoisfleuret · 2026-11-12
- Recursive bets on open-endedness: agents running massive parallel experiments like scientist communities — agihouse_org · 2026-11-12
- Recursive's Tim Shi maps recursive self-improvement: from learning data to discovering architectures — agihouse_org · 2026-11-12
- New essay argues design is a search problem — AI speeds exploration but that may not find optimal solutions — round · 2026-11-12