Technology
Reinforcement learning from human feedback
Shaping a model's behaviour from human ratings and preferences.
3
mentions in the archive
0
central to an episode
3
episodes with a mention
0
fragments with a timecode
Jan 2025
first mention
Jan 2025
peak · 1 in a month
85
links to other entries
Author's trends
In the episodes of the author's 20 thoughts, Reinforcement learning from human feedback is never central or discussed in depth, and the author's quotes don't mention the name.special·4 Mar 2026brief mention✓ article
AI Safety Is Not a Fight Against an “Evil Model,” but a Fight Over the Right of People and States to Set Its RulesMentions over time
202420252026