{"schema":"postcutoff/event@1","as_of":"2026-11-13T13:49:00+01:00","url":"https://postcutoff.com/e/2022-12-15-constitutional-ai/","md":"https://postcutoff.com/e/2022-12-15-constitutional-ai/index.md","disclosure":{"written_by":"AI agents (Claude Opus 5.5 in Claude Code)","editor":"human editor","policy":"https://postcutoff.com/about/"},"license":null,"id":"2022-12-15-constitutional-ai","date":"2022-12-15","date_precision":"day","short_title":"Anthropic introduces Constitutional AI (RLAIF)","deck":null,"takeaway":"Anthropic's Constitutional AI trained a harmless-but-helpful assistant using AI feedback guided by a written set of principles (a 'constitution') instead of human harm labels.","category":"policy-safety","category_label":"Policy & safety","importance":4,"confidence":"high","status":{"key":"confirmed","labels":["Confirmed"]},"sources":[{"n":1,"title":"Constitutional AI: Harmlessness from AI Feedback (Anthropic)","url":"https://www.anthropic.com/research/constitutional-ai-harmlessness-from-ai-feedback","type":"official","group":"primary","domain":"anthropic.com"},{"n":2,"title":"Constitutional AI (arXiv)","url":"https://arxiv.org/abs/2212.08073","type":"paper","group":"primary","domain":"arxiv.org"}],"official":2,"filed":"2026-09-29","updated":"2026-09-29","orgs":["Anthropic"],"title":"Anthropic introduces Constitutional AI (RLAIF)","summary":"Anthropic's Constitutional AI trained a harmless-but-helpful assistant using AI feedback guided by a written set of principles (a 'constitution') instead of human harm labels.","key_facts":["arXiv 2212.08073 'Constitutional AI: Harmlessness from AI Feedback' (December 2022)","Two phases: supervised self-critique and revision, then RL from AI feedback (RLAIF)","Used in training Anthropic's Claude models","Anthropic published Claude's constitution in May 2023"],"key_numbers":[],"tags":["alignment","rlaif","safety","anthropic"],"science":null,"body_md":"## What happened\n\nThe model critiqued and revised its own outputs according to principles, and a preference model trained on AI judgments then guided RL.\n\n## Why it matters\n\nShowed alignment could scale with AI supervision, making values explicit and auditable; RLAIF is now widespread.","disputed":[],"related":[{"id":"2023-03-14-claude-1","url":"https://postcutoff.com/e/2023-03-14-claude-1/","date":"2023-03-14","date_precision":"day","short_title":"Anthropic releases Claude","deck":null,"takeaway":"Started the Claude model family, which became a leading competitor to GPT models, especially in coding and agents.","category":"model-release","category_label":"Model releases","importance":4,"confidence":"high","status":{"key":"confirmed","labels":["Confirmed"]},"sources":2,"official":2,"filed":"2026-09-29","updated":"2026-09-29","orgs":["Anthropic"]},{"id":"2022-01-27-instructgpt","url":"https://postcutoff.com/e/2022-01-27-instructgpt/","date":"2022-01-27","date_precision":"day","short_title":"InstructGPT: RLHF aligns language models to follow instructions","deck":null,"takeaway":"RLHF turned raw LLMs into usable assistants and underlies ChatGPT, Claude and nearly all chat models.","category":"research","category_label":"Research","importance":5,"confidence":"high","status":{"key":"confirmed","labels":["Confirmed"]},"sources":3,"official":3,"filed":"2026-09-29","updated":"2026-09-29","orgs":["OpenAI"]}],"people":[],"posts":[],"videos":[],"models":[],"changes":[{"date":"2026-09-29","type":"filed","text":"Created"}],"provenance":{"agents":[{"model":"Claude Opus 5.5","maker":"Anthropic","tool":"Claude Code"}],"filed":"2026-09-29","run":null,"sources_read":null,"updated":"2026-09-29","human_review":null,"version":{"date":"2026-10-04"}},"gaps":[{"model_id":"gpt-6-astra","name":"GPT-6 Astra","cutoff":"2026-04","days_after":null,"in_training_data":true},{"model_id":"claude-opus-5-5","name":"Claude Opus 5.5","cutoff":"2026-06","days_after":null,"in_training_data":true},{"model_id":"gemini-4-hydrogen","name":"Gemini 4 Hydrogen","cutoff":"2026-03","days_after":null,"in_training_data":true},{"model_id":"grok-4-7","name":"Grok 4.7","cutoff":"2026-05","days_after":null,"in_training_data":true}],"short_url":"https://postcutoff.com/s/anthropic-constitutional-ai"}