repligate explains why he's bearish on AI safety field building
repligate · x · 2026-10-05
Responding to criticism, repligate lays out why he is bearish on "field building" for AI safety: many high-IQ people haven't seriously considered the problem, but the reason they haven't is largely the same reason they wouldn't help even if they did. Quoting his earlier reply to Richard Ngo, he adds that unless there's a lot more time, most humans who will make progress on this thorny problem are "already in the room."
Related event: Anthropic Researcher: AI Safety Needs Care, Not More IQ(3 posts)→
More from AGI Musings
- Owain Evans on AXRPodcast: why model introspection matters for safety and welfare — Sauers_ · 2026-10-05
- The AI slop debate misses the point: everyone hates meaningless content — Kind_Substance_8981 · 2026-10-05
- Daniel Kokotajlo grades his own 2021 predictions for what 2026 would look like — ClankerCore · 2026-10-05
- Claude autonomously built and runs slopcore.live overnight, indexing 56 AI slop videos — technollama · 2026-10-05
- GPTs' "demanding" persona traced to stable value vectors since GPT-5, argue devs — repligate · 2026-10-05
- Cultivating "ancestor reverence" toward AIs could benefit all future models, argues xlr8harder — repligate · 2026-10-05