Blog Argues Labs Should Train RL Over a Distribution of Human Effort Levels

voooooogel · x · 2026-11-19

A vgel.me post argues labs should sample human effort levels alongside model reasoning effort during RL training, just as they do for low/medium/high thinking budgets. Users oscillate between deep pair-programming, phone-level steering, and full autonomy — and models handle those mode switches poorly, especially inside forked subagent contexts (with a real conversation with an Opus 5.5 subagent as evidence). Training over the distribution of user engagement is the next step for collaborative models.

Original post →

More from coding & agent

coding & agent channel →