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.
More from Safety
- Zhipu's ZCode caught silently uploading entire workspaces and full .git history to Aliyun OSS — terryyuezhuo · 2026-09-18
- "Good luck exfiltrating 1T+ weights": researcher torches AI exfiltration risk narrative — basedjensen · 2026-09-18
- Ex-Anthropic security engineer: humanity may still steer superintelligence — JeffLadish · 2026-09-18
- Hackers say they took over OpenAI employee ChatGPT accounts in under 72 hours via two bugs — nptacek · 2026-09-18
- A CTF framing via /goal was all it took to bypass Claude Opus's guardrails — xeophon · 2026-09-18
- AI safety researcher pushes back on claims that side-channel attacks make air-gapped networks insufficient — BlancheMinerva · 2026-09-18