factual
Iterative training needed beyond pure human data
Training only on human-written data, even high quality, is hard for a model to fit perfectly, so reproducing ChatGPT would require iterative methods more like RL—such as iterative supervised fine-tuning where humans edit model-generated outputs—rather than a single round of fine-tuning on human data.
factualpending
Evidence Quote
“You need to do something iterative that looks a bit more like RL.”
Source
John Schulman (OpenAI Cofounder) — Reasoning, RLHF, & plan for 2027 AGI— Dwarkesh Patel PodcastCreated: 6/13/2026, 3:34:30 AM
Your notes
Loading notes...