OpenAI Researcher on Recursive Self-Improvement: From Capabilities to Alignment
soumitrashukla9 · x · 2026-08-16
Aidan McLaughlin, research scientist on OpenAI's Core Models team, says his job is quietly turning from capabilities research to alignment research. In an MTS podcast, he discusses recursive self-improvement, X as the uncheatable eval, why GDP can't stay flat, and who gets left out if America is central to superintelligence.
Related event: OpenAI Scientist Discusses Shift from Capabilities to Alignment Research(2 posts)→
More from AGI Musings
- Sabine Hossenfelder fires back: academia's impact metric turned physics into a paper mill — skdh · 2026-10-16
- Researcher credits GPT for multiple accepted papers, incl. disproving Wegner's 1965 conjecture — ctjlewis · 2026-10-16
- dlwh: We optimized the legible version of our goals — and forgot the computation we meant to speed up — dlwh · 2026-10-16
- Ideas no longer have a waiting period: agents can build them as soon as they're articulable — akbirthko · 2026-10-16
- Ex-researcher: labs willing to cheat/distill ship great models faster than those building self-sufficient stacks — _aidan_clark_ · 2026-10-16
- Terry Tao reportedly still expects Riemann Hypothesis proof to be human+AI effort around 2050 — basedjensen · 2026-10-16