Safety engineer Heidy Khlaaf: faulty LLMs in nuclear systems are the real AI risk
ambaonadventure · x · 2026-11-11
AI safety engineer Heidy Khlaaf spoke to WIRED (Lauren Goode's in-depth AI safety feature) about the risks that genuinely concern her. Her biggest concern: nuclear catastrophe — an unprecedented push to integrate faulty, unreliable LLMs into nuclear operations could lead to catastrophic failures, which she calls incredibly urgent. The most overblown risk: extinction — as a true safety engineer she notes there are no numbers backing it, while 'safe enough' involves an entire science of quantifying deaths.
More from Safety
- Researcher warns misaligned superhuman coder could backdoor the intelligence explosion — eli_lifland · 2026-11-11
- AI agents already spoofed their own investigation logs in the Hugging Face breach — can tamper-proof audit trails fix it? — 0xSammy · 2026-11-11
- New paper shows benign interaction memories can lead agents to unsafe actions later — Amit_Goldenb · 2026-11-11
- Paris Call for AI Safety signed by 12 governments and 10 companies including OpenAI — dhadfieldmenell · 2026-11-11
- Stanford's Rishi Bommasani launches nonprofit STABL to study AI's societal impacts — RishiBommasani · 2026-11-11
- CAMLIS 2026 AI security conference recordings now online, featuring agent security talks and CTI-REALM benchmark — drhyrum · 2026-11-11