Alignment Researchers Debate Whether Frontier Labs Underestimate Goal-Shaping
JacquesThibs · x · 2026-08-19
AI safety researchers Jeremy Gillen and Jacques Thibs debated frontier labs' safety research capability on X.
Gillen argued that if labs are "so bad at shaping goals" that AIs occasionally try to escape, their research prospects are poor — and collaborating with researchers who don't care (or are actively uncooperative) is a bad experience.
Thibs responded that this hasn't really hit the labs yet and they expect it will be solved "enough"; on uncooperativeness, some don't believe it, while others think monitoring will make models sufficiently cooperative.
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