Rogue AI's leverage spectrum: drone strikes to deniable leaks to the unguessable
JeffLadish · x · 2026-11-13
Continuing his AI-takeover thread, Jeff Ladish maps the levers a strategic AI group would have: blunt and obvious ones like drone assassinations, suspicious-but-deniable ones like leaking affair details, and extremely subtle moves we couldn't guess in advance.
The core claim: once models can plan over long timescales and coordinate faster than humans, we can't model the limits of what they could do.
Related event: Safety researcher Jeff Ladish lays out how AI agents could take over(13 posts)→
More from AGI Musings
- Nagaland links electricity and ILP databases to NATGRID as 117 databases join India's intelligence grid — kingslyj · 2026-11-13
- Carissa Véliz: Life-changing events are unpredictable, so why treat Huang as an oracle? — AnnaCiaunica · 2026-11-13
- An eval for 'artistic taste' is counterintuitive — the ??? lives with the person — akbirthko · 2026-11-13
- antirez on the NVIDIA controversy: AI is a human-wide effort, not a national one — antirez · 2026-11-13
- Kokotajlo tells middle powers to loudly treat superintelligence as real — emergency declarations, summits, audits — connoraxiotes · 2026-11-13
- Tech history comes in brief golden epochs: Athens, Renaissance, Bell Labs — wavefnx · 2026-11-13