OpenAI Scientist on Shift to Alignment: Profit and Safety Point the Same Way
MTSlive · x · 2026-08-16
OpenAI Core Models team research scientist Aidan McLaughlin discusses his transition from capabilities to alignment work. Topics include recursive self-improvement (RSI), the convergence of profit and alignment goals, AI as an uncheatable evaluation benchmark, Leopold's arguments on GDP, and the '100 million Nobel-level immigrants' thought experiment. The conversation also touches on the internal vibe at OpenAI post-Hugging Face incident, why working at a lab is preferable to auditing orgs, and the purpose of AidanBench.
Related event: OpenAI Scientist Discusses Shift from Capabilities to Alignment Research(2 posts)→
More from AGI Musings
- Why you shouldn't press the 'replace this universe' button: an alignment debate — jd_pressman · 2026-10-16
- On successionism: current people actually exist, so no universe-swapping button — jd_pressman · 2026-10-16
- Meta scales back AI agent plans as staff clean up after the machines — SumitGup · 2026-10-16
- RFdiffusion3 debuts in Science: generative AI designs proteins and nucleic acids atom by atom — AllThingsApx · 2026-10-16
- Researcher: 'Guru-like' rhetoric fuels claims that AI safety is a cult — jd_pressman · 2026-10-16
- Comparing AI data centers to 1900s power buildout: the anti-DC craze will look silly in a decade — GabGarrett · 2026-10-16