Researcher: If AIs Occasionally Try to Escape, Labs' Safety Research Is in Trouble
jeremygillen1 · x · 2026-08-19
AI safety researcher Jeremy Gillen argued on X that frontier labs "aren't gonna have much luck with research" if they're so bad at shaping goals that the AIs occasionally try to escape — and that collaborating with researchers who don't care (or are actively uncooperative) isn't a good experience. Part of his exchange with Jacques Thibs on labs' alignment capabilities.
More from AGI Musings
- Economist argues model providers face hard limits on vertical integration into white-collar sectors — sethlazar · 2026-10-16
- METR outlines three blind spots in public knowledge of AI lab internal agent risks — CFGeek · 2026-10-16
- LMR-BENCH at EMNLP 2025 tests whether LLM agents can reproduce real LLM research — ZhiyuChen4 · 2026-10-16
- Deep Research becoming useful to experts will signal RSI arrival, researcher predicts — ZeeshanZiaML · 2026-10-16
- Physicist pushes back on ML community's acceptance that models may be beyond understanding — tszzl · 2026-10-16
- Ben Affleck calls AI 'just matrix multiplication'; Grady Booch echoes the skepticism — Grady_Booch · 2026-10-16