{"id":"clm_6DC1EF4EB712","entity":"openai","predicate":"released","value":"RL-Teacher","value_json":{"feed":"openai-news","item":"https://openai.com/index/gathering-human-feedback","tags":{"v":2,"ai":true,"by":"claude-haiku-5-5","on":"2026-11-03","themes":["safety_policy","reasoning"],"release_kind":"developer_tool"},"check":{"on":"2026-11-04","url":"https://openai.com/index/gathering-human-feedback","read":"feed","pages":1,"quote":"RL-Teacher is an open-source implementation of our interface to train AIs via occasional human feedback rather than hand-crafted reward functions.","outcome":"checked"},"evidence":"RL-Teacher is an open-source implementation of our interface to train AIs via occasional human feedback rather than hand-crafted reward functions. The underlying technique was developed as a step towards safe AI systems, but also applies to reinforcement learning problems with rewards that are hard ","extracted_by":"claude-haiku-5-5","primary_source":true},"valid_from":"2017-08-03","valid_to":null,"published":"2017-08-03","recorded":"2026-11-03","confidence":0.7,"status":"valid","assertable":true,"superseded_by":null,"supersedes":[],"first_seen_at":"2026-11-03T23:55:38.749992+00:00","updated_at":"2026-11-04T01:09:03.345166+00:00","sources":[{"url":"https://openai.com/index/gathering-human-feedback","tier":"primary","publisher":"OpenAI","published_at":"2017-08-03T00:00:00+00:00"}],"evidence":{"by":"page-read","on":"2026-11-04","quote":"RL-Teacher is an open-source implementation of our interface to train AIs via occasional human feedback rather than hand-crafted reward functions.","url":"https://openai.com/index/gathering-human-feedback","read":"feed","excerpt":"RL-Teacher is an open-source implementation of our interface to train AIs via occasional human feedback rather than hand-crafted reward functions. The underlying technique was developed as a step towards safe AI systems, but also applies to reinforcement learning problems with rewards that are hard"},"legend":{"dates":"valid_from: when the claim took effect (a period figure: the day its period closed). published: the earliest day a source on the record published it (a filing's filing date, a post's date; null when no source carries one). recorded: the day AsOf first held it. A figure can take effect weeks before it is published.","why_not":{},"checked_by":{"page-read":"its source page states the value and the date"}}}