OpenAI's RLSlow team: how RL for reasoning earned conviction and scaled
lukaszkaiser · x · 2026-09-07
Former OpenAI researcher Lukasz Kaiser paid tribute to the RLSlow team, whose name nods to Thinking, Fast and Slow: LLMs already had "fast" thinking (immediate answers), and RL could teach them "slow" thinking — deliberate, multi-token reasoning that spends more compute. TrapitBansal recalls how early the team developed real conviction, spending long nights babysitting runs and designing careful experiments, with early discussions alongside Ilya Sutskever and later Jakub Pachocki. Evidence pushed them early to a strong view: RL for reasoning would scale. Kaiser thanks the full roster spanning the foundations of reasoning (later project "berry") onward, including Francis Song, Suchir Balaji and Dan Selsam.
Related event: Ex-OpenAI researcher Kaiser reflects on the RLSlow team's journey(3 posts)→
More from Companies & People
- Oxford Martin AIGI hiring two technical AI verification researchers, visas sponsored — wfithian · 2026-10-27
- AfterQuery launches Data Partnerships, betting frontier models have exhausted public web data — ycombinator · 2026-10-27
- Economist Bharat Chandar named Research Director for AI Economics at Stanford Digital Economy Lab — RishiBommasani · 2026-10-27
- Menlo Ventures partner recalls bending VC rules to back pre-launch Anthropic at $4B — mmurph · 2026-10-27
- MIT Tech Review dissects Anthropic's narrative strategy as its $1.5T IPO lands — MIT Tech Review AI · 2026-10-27
- Google DeepMind Frontier Computation team recruits PhD student researchers in London — PetarV_93 · 2026-10-27