{"adoption": {"forks": 254, "observed_at": "2026-08-28T04:06:39.699961+00:00", "stars": 2345}, "canonical_url": "https://ross.abutalabs.com/products/rlhf-book", "card": {"archived": false, "artifact_type": "learning-resource", "description": "Textbook on reinforcement learning from human feedback", "domain": ["large-language-models", "machine-learning", "tutorials", "education"], "enriched": true, "function": ["machine-learning", "llm-training", "developer-tools"], "health_score": 99, "homepage": "https://rlhfbook.com/", "language": "Python", "license": "NOASSERTION", "license_family": "other", "maturity": "active", "member_repos": ["natolambert/rlhf-book"], "name": "natolambert/rlhf-book", "platform": ["python", "cross-platform"], "pushed_at": "2026-08-21T11:09:09+00:00", "repo": "natolambert/rlhf-book", "stars": 2345, "tags": ["rlhf", "post-training", "textbook", "reinforcement-learning", "preference-learning", "open-source-book"], "topics": ["ai", "alignment", "rlhf"], "urls": [], "use_cases": ["learn how RLHF works from first principles", "understand LLM post-training techniques like DPO and PPO", "study reference implementations of reward model training", "prepare for a career in LLM alignment or fine-tuning", "find a canonical reference for rejection sampling and GRPO", "teach a course on language model alignment"], "what_it_is": "An open-source textbook on Reinforcement Learning from Human Feedback (RLHF) and LLM post-training, available online and in print, with companion reference code implementations. It covers instruction tuning, reward modeling, policy gradients (PPO, GRPO, DPO), rejection sampling, and distillation.", "when_to_avoid": ["you need a production-ready RLHF training framework", "you want a maintained software library with API stability guarantees", "you need hands-on tooling rather than conceptual explanations"], "when_to_choose": ["you want a comprehensive, curated introduction to RLHF and post-training", "you need runnable reference code for RLHF algorithms", "you prefer learning from a structured book with a community and course materials"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/rlhf-book", "repo": "natolambert/rlhf-book", "role": "main", "score": 89}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:06:39.699961+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T02:37:03.249560+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1cdbf3dd5dcc4d7b837682dc642baf27af364debe196747395e0e0e068543209", "fetched_at": "2026-08-28T04:06:39.699961+00:00", "kind": "readme", "missing": false, "url": "https://github.com/natolambert/rlhf-book"}, {"content_hash": "9d4b17ddb257593852356bbe9c3fe6cf3b4f7a379c52c32c489f43b42565a8a4", "fetched_at": "2026-08-29T10:17:38.010613+00:00", "kind": "homepage", "missing": false, "url": "https://rlhfbook.com/"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:06:39.699961+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T02:37:03.249560+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1cdbf3dd5dcc4d7b837682dc642baf27af364debe196747395e0e0e068543209", "fetched_at": "2026-08-28T04:06:39.699961+00:00", "kind": "readme", "missing": false, "url": "https://github.com/natolambert/rlhf-book"}, {"content_hash": "9d4b17ddb257593852356bbe9c3fe6cf3b4f7a379c52c32c489f43b42565a8a4", "fetched_at": "2026-08-29T10:17:38.010613+00:00", "kind": "homepage", "missing": false, "url": "https://rlhfbook.com/"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T02:37:03.249560+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1cdbf3dd5dcc4d7b837682dc642baf27af364debe196747395e0e0e068543209", "fetched_at": "2026-08-28T04:06:39.699961+00:00", "kind": "readme", "missing": false, "url": "https://github.com/natolambert/rlhf-book"}, {"content_hash": "9d4b17ddb257593852356bbe9c3fe6cf3b4f7a379c52c32c489f43b42565a8a4", "fetched_at": "2026-08-29T10:17:38.010613+00:00", "kind": "homepage", "missing": false, "url": "https://rlhfbook.com/"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:06:39.699961+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:06:39.699961+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:06:39.699961+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T02:37:03.249560+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1cdbf3dd5dcc4d7b837682dc642baf27af364debe196747395e0e0e068543209", "fetched_at": "2026-08-28T04:06:39.699961+00:00", "kind": "readme", "missing": false, "url": "https://github.com/natolambert/rlhf-book"}, {"content_hash": "9d4b17ddb257593852356bbe9c3fe6cf3b4f7a379c52c32c489f43b42565a8a4", "fetched_at": "2026-08-29T10:17:38.010613+00:00", "kind": "homepage", "missing": false, "url": "https://rlhfbook.com/"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:06:39.699961+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:06:39.699961+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T02:37:03.249560+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1cdbf3dd5dcc4d7b837682dc642baf27af364debe196747395e0e0e068543209", "fetched_at": "2026-08-28T04:06:39.699961+00:00", "kind": "readme", "missing": false, "url": "https://github.com/natolambert/rlhf-book"}, {"content_hash": "9d4b17ddb257593852356bbe9c3fe6cf3b4f7a379c52c32c489f43b42565a8a4", "fetched_at": "2026-08-29T10:17:38.010613+00:00", "kind": "homepage", "missing": false, "url": "https://rlhfbook.com/"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:06:39.699961+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:06:39.699961+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:06:39.699961+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T02:37:03.249560+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1cdbf3dd5dcc4d7b837682dc642baf27af364debe196747395e0e0e068543209", "fetched_at": "2026-08-28T04:06:39.699961+00:00", "kind": "readme", "missing": false, "url": "https://github.com/natolambert/rlhf-book"}, {"content_hash": "9d4b17ddb257593852356bbe9c3fe6cf3b4f7a379c52c32c489f43b42565a8a4", "fetched_at": "2026-08-29T10:17:38.010613+00:00", "kind": "homepage", "missing": false, "url": "https://rlhfbook.com/"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:06:39.699961+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:06:39.699961+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T02:37:03.249560+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1cdbf3dd5dcc4d7b837682dc642baf27af364debe196747395e0e0e068543209", "fetched_at": "2026-08-28T04:06:39.699961+00:00", "kind": "readme", "missing": false, "url": "https://github.com/natolambert/rlhf-book"}, {"content_hash": "9d4b17ddb257593852356bbe9c3fe6cf3b4f7a379c52c32c489f43b42565a8a4", "fetched_at": "2026-08-29T10:17:38.010613+00:00", "kind": "homepage", "missing": false, "url": "https://rlhfbook.com/"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T02:37:03.249560+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1cdbf3dd5dcc4d7b837682dc642baf27af364debe196747395e0e0e068543209", "fetched_at": "2026-08-28T04:06:39.699961+00:00", "kind": "readme", "missing": false, "url": "https://github.com/natolambert/rlhf-book"}, {"content_hash": "9d4b17ddb257593852356bbe9c3fe6cf3b4f7a379c52c32c489f43b42565a8a4", "fetched_at": "2026-08-29T10:17:38.010613+00:00", "kind": "homepage", "missing": false, "url": "https://rlhfbook.com/"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T02:37:03.249560+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1cdbf3dd5dcc4d7b837682dc642baf27af364debe196747395e0e0e068543209", "fetched_at": "2026-08-28T04:06:39.699961+00:00", "kind": "readme", "missing": false, "url": "https://github.com/natolambert/rlhf-book"}, {"content_hash": "9d4b17ddb257593852356bbe9c3fe6cf3b4f7a379c52c32c489f43b42565a8a4", "fetched_at": "2026-08-29T10:17:38.010613+00:00", "kind": "homepage", "missing": false, "url": "https://rlhfbook.com/"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T02:37:03.249560+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1cdbf3dd5dcc4d7b837682dc642baf27af364debe196747395e0e0e068543209", "fetched_at": "2026-08-28T04:06:39.699961+00:00", "kind": "readme", "missing": false, "url": "https://github.com/natolambert/rlhf-book"}, {"content_hash": "9d4b17ddb257593852356bbe9c3fe6cf3b4f7a379c52c32c489f43b42565a8a4", "fetched_at": "2026-08-29T10:17:38.010613+00:00", "kind": "homepage", "missing": false, "url": "https://rlhfbook.com/"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 98, "longevity": 59, "rhythm": 96}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": ["no_license"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 831, "days_push": 12, "days_rel": 26, "gap_med": 18, "n_releases_24m": 12}, "score": 89, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}