Ex-OpenAI Staffer Leaves to Tackle LLM Generalization with RL Data

Former OpenAI employee Andrew Ho left to start a company focused on high-quality reinforcement learning (RL) datasets. He criticized current LLMs for their poor generalization despite massive investments, calling advanced RL data the key to breaking current bottlenecks.

2026-07-30 ~ 2026-07-31 · 4 related posts

• Ex-OpenAI Staffer Leaves to Build High-Quality RL Data Startup, Cites Poor LLM Generalization — panickssery · 2026-07-30
• Ex-OpenAI Staffer Starts RL Data Firm, Calls Lab Valuations Delusional — AI寒武纪 · 2026-07-30
• Ex-OpenAI Employee Starts Company for High-Quality RL Datasets, Citing Poor LLM Generalization — burny_tech · 2026-07-31

1 near-duplicate retellings: rickasaurus