Ex-OpenAI researcher Lukasz Kaiser pens farewell to RLSlow reasoning team
RubenEVillegas · x · 2026-09-07
Former OpenAI researcher Lukasz Kaiser posted a lengthy farewell to the RLSlow (reinforcement learning slow-thinking) team, which he led — first alongside Ilya Sutskever, then with Merettm, and finally on his own. The team began with work on the foundations of reasoning (later the 'berry' project), with members including Trapit Bansal and Francis Song. Colleagues noted Kaiser was leading RL work in brain research back when transformers were only 200M parameters. The tribute offers a rare glimpse into the organizational history behind OpenAI's reasoning research.
Related event: Ex-OpenAI Researcher Lukasz Kaiser Bids Farewell to RLSlow Team(2 posts)→
More from Companies & People
- Clara Shih on when students should start using AI: once you can judge the output — clarashih · 2026-09-07
- Claude Code's Boris Cherny: don't optimize token cost, maximize returns — rohanpaul_ai · 2026-09-07
- OpenAI agent security engineer: alignment window is narrow, community must step up — Scobleizer · 2026-09-07
- RLSlow team credited with inventing RL at scale for LLMs — morqon · 2026-09-07
- Paul Graham: Founders' strength comes from having experienced weakness — santoshpanda · 2026-09-07
- AI researchers spend their days debugging 'incomprehensible' training code, engineer says — gabrielchua · 2026-09-07