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.

Original post →

More from AGI Musings

AGI Musings channel →