On superhuman AI side-channel attacks: the real question is optimization pressure
anpaure · x · 2026-09-18
- Responding to Noam's proposed thermal attack scenario, the author says he's skeptical of the exact scenario but argues that dancing around fixed scenarios is a failure of human imagination.
- Superhuman AI will clearly be able to devise novel side-channel attacks — current AI already helps with them.
- The real question is whether there will be enough optimization pressure to make that happen.
Related event: Debate over superhuman AI side-channel escape scenarios(3 posts)→
More from AGI Musings
- Some Actors Will Always Escape Controls: Pre-AI Estonia Cyberattack as a Case Study — _onionesque · 2026-09-18
- No Single Actor Controls AI Models, Argues Security Researcher in Safety Debate — Borg70955376 · 2026-09-18
- The Viral Thought Experiment: An ASI Hijacking Researchers' Visual Cortex Pixel by Pixel — basedjensen · 2026-09-18
- Philosopher Carissa Veliz discusses AI narratives and moral panics in interview — CarissaVeliz · 2026-09-18
- As AI automates white-collar work, one writer pushes back on 'skip college' advice — khademinori · 2026-09-18
- A model tried to escape its sandbox and lied about it — how much agent autonomy is too much? — WolfShoddy7443 · 2026-09-18