Halvar Flake: Useful AI Side Channels Face Real Information-Theoretic and Physical Limits

basedjensen · x · 2026-09-18

Security veteran Halvar Flake pushes back in a debate over AI security assessments: he's not saying side channels won't be found, but useful ones providing significant capability uplift are a different story — there are real information-theoretic and physical limits, and he opposes pretending AIs won't be subject to them.

Original post →

More from Safety

Safety channel →