Geoffrey Irving: air gaps may matter someday but are laughably far from AI companies' current security
geoffreyirving · x · 2026-09-18
Alignment researcher Geoffrey Irving weighs in on the air-gap debate: it may be important for the future, but it is "laughably far from being relevant" to the level of security AI companies actually have today.
His point: keep the two separate — don't conflate speculative frontier security needs with a description or critique of current industry practice.
More from Safety
- "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
- 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