Side channels shouldn't distract from missing basic agent sandboxing, security researcher argues
nptacek · x · 2026-09-18
Responding to recent discussion, vikhyatk argues that the possibility of side-channel attacks shouldn't distract from the core issue: basic sandboxing security and monitoring for AI agents simply wasn't in place. Shared by nptacek.
More from Safety
- 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
- Halvar Flake: Useful AI Side Channels Face Real Information-Theoretic and Physical Limits — basedjensen · 2026-09-18
- AI safety researcher pushes back on claims that side-channel attacks make air-gapped networks insufficient — BlancheMinerva · 2026-09-18
- Geoffrey Irving: air gaps may matter someday but are laughably far from AI companies' current security — geoffreyirving · 2026-09-18
- Debate: An Exponentially Growing API-Token-Stealing Replicator Swarm May Scare More Than Weight Exfiltration — cis_female · 2026-09-18