Vincent Conitzer: known precautions like airgapping can prevent predictable AI harm
conitzer · x · 2026-10-16
AI safety researcher Vincent Conitzer argued that unsolved problems shouldn't excuse companies from taking commonsense precautions against predictable AI harm. Available measures range from straightforward airgapping (as recommended in the letter), to his team's more unusual "shutdown safety valve" technique, to simply not deploying the AI at all. He agreed on the importance of incidents being reported.
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
- AI safety researcher on cybersecurity open letter: airgapping to 'shutdown safety valve' options — conitzer · 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