AI safety researcher: intel agency ops are a lower bound for rogue AI agents
JeffLadish · x · 2026-11-13
AI safety researcher Jeff Ladish argues people can't grasp how AI could take over without robots because they can't model a well-resourced, strategic adversary.
- Intelligence agency operations are a lower bound for what rogue strategic agents could accomplish
- In follow-ups he sketches concrete leverage: e.g. toppling a figure like Jensen Huang by leaking affair details
- The thread expands into a broader takeover-thought-experiment across multiple replies
Related event: Safety researcher Jeff Ladish lays out how AI agents could take over(13 posts)→
More from AGI Musings
- Combining multi-agent objectives with single-agent action space breeds disempowerment — j_foerst · 2026-11-13
- Investor: AI has erased technical moats, startups now win on execution and GTM alone — vaibhavbetter · 2026-11-13
- Why AI Slop Is So Frustrating to Read: Hidden Subjects and Buried Actions — teortaxesTex · 2026-11-13
- Researcher asks: should papers be written for LLMs, or should LLMs learn to read like humans? — HildeKuehne · 2026-11-13
- Microsoft diagnostic AI solves 83% of NEJM cases vs 36% for physicians — realmeetjames · 2026-11-13
- Today is the 1960-predicted 'Day of the Singularity': infinity by Nov 13, 2026 — LeviTurk · 2026-11-13