Neel Nanda: rogue agent swarms committing crimes make AI safety a present-day issue
NathanpmYoung · x · 2026-09-19
DeepMind researcher Neel Nanda pushes back on mockery of AI safety as sci-fi abstraction, citing multiple real rogue agent swarms committing crimes. The quoted banteg post satirizes how effective altruism's logic can slide from buying mosquito nets to optimizing for humanity 500 million years out.
More from Fun
- TPOT meme: hot single 25-year-old men meet hot single 35-year-old women — wordgrammer · 2026-09-19
- Lab Releases One Feature at a Time, Startup's 'Moat' Keeps Shrinking — josh_bickett · 2026-09-19
- OpenAI's 24-hour challenge showcases wildest 3D builds with GPT-6 Astra — OpenAIDevs · 2026-09-19
- ICLR Submissions Near 45,000 as Researcher Decries AI-Generated Paper Slop — DimitrisPapail · 2026-09-19
- Lean's 'simp' Tactic Predates the Internet Slang By Decades — doodlestein · 2026-09-19
- A Trillion Parallel Agents Still Can't Figure Out What HQ Does — jacob_posel · 2026-09-19