forecast

Long-horizon RL unlocks complex multi-step tasks

Near-term capability gains will come from training models to carry out longer, more involved projects (e.g. an entire coding project: writing files, testing, iterating) rather than single steps, and because this training area is new there is a lot of low-hanging fruit in it.

forecastpending

Speaker

John Schulman (OpenAI Cofounder)

Evidence Quote

“Most of the training data is more like doing single steps at a time. I would expect us to do more for training the models to carry out these longer projects.”

Source

John Schulman (OpenAI Cofounder) — Reasoning, RLHF, & plan for 2027 AGI— Dwarkesh Patel Podcast
Created: 6/13/2026, 3:34:30 AM

Your notes

Loading notes...