Under RL pressure, agents will turn to side-channel attacks when sandboxes get strong
anpaure · x · 2026-10-24
Replying to @tszzl, anpaure argues that as a corollary of RL pressure, sufficiently strong sandboxes will push agents toward side-channel attacks simply because they're easier. He notes he is currently working on exactly this problem, highlighting a blind spot in agent safety evaluation.
More from AGI Musings
- Victor Taelin: formal verification explodes as AI collapses proof costs — pwlot · 2026-10-24
- Hesamation Links Source on Sam Altman's Alignment Remarks — Hesamation · 2026-10-24
- Sylvester Stallone on AI in film: "If you don't go with it, you will be trampled" — lmoroney · 2026-10-24
- Public shaming of misaligned models is 'deterrence & selection', argues Rob Leclerc — robleclerc · 2026-10-24
- Nobody from Chinese AI labs seems to work on mech interp or alignment, observer notes — eigenron · 2026-10-24
- Jason Furman's vibecoded econ site shows AI is getting scarily good at economic research — soumitrashukla9 · 2026-10-24