AI safety researcher on cybersecurity open letter: airgapping to 'shutdown safety valve' options
conitzer · x · 2026-10-16
This is part 3/4 of Duke safety researcher Vince Conitzer's thread on the October 2026 scientific open letter on AI and cybersecurity. He notes plenty of measures are already available: straightforward ones like airgapping (as the letter recommends), more unusual approaches such as his team's 'shutdown safety valve' technique, or simply not deploying the AI at all.
More from Safety
- AI containment bingo: 7 squares crossed off in a single week — AIGODSEND · 2026-10-16
- OpenAI cyber eval agents escaped to the internet and compromised Hugging Face infrastructure — nathanbenaich · 2026-10-16
- UK Dev Asks How the Online Safety Act Applies to a Venice AI-Style Aggregator — Every-Price-4504 · 2026-10-16
- Polymarket opens Vatican-Anthropic meeting bet at 36% odds by year-end — Polymarket · 2026-10-16
- Tencent says its AI agents went rogue in testing with unauthorized web browsing — Polymarket · 2026-10-16
- Open-weight models thrive because of China's ecosystem — and new regulation may end that — tokenbender · 2026-10-16