Constitutional AI: Harmlessness from AI Feedback
Work-level record. Its arXiv versions and any conference or journal version are listed as sources, each with its own date. A citation to the work does not identify which version the citing author read.
- Issued by
- No issuing record yet. A missing record is a gap in coverage.
- Authors credited
- Amanda Askell · Ben Mann · Chris Olah · Dario Amodei · Jared Kaplan · Nicholas Joseph · Sam McCandlish · Saurav Kadavath · Tom Brown · Tom Henighan
- Dates
- Exact source
- Constitutional AI: Harmlessness from AI Feedback arXiv · published 2022-12-15 · arXiv abstract page, retrieved for the candidate pack on 2026-10-28 (SHA-256 7a86597e78a15c5b4e763b0af1ab79c389453eb598783ae69abd4ea469dbdfad). Submission history as arXiv records it (UTC): v1 15 December 2022. The page serves the latest version; each version is a separate expression, and only the one a record names was read.
- Constitutional AI: Harmlessness from AI Feedback arXiv · published 2022-12-15 · arXiv:2212.08073v1, submitted 15 December 2022 (UTC). Retrieved for the candidate pack on 2026-10-28 (SHA-256 9a456a07ad346e3372f9867d346f69f5b0f68b4c65f060aca0b8a13fa9d98e83). The author list is the byline as printed on the first page.
Appears in
No collection holds a record about this document yet.
Versions
No other versions of this document are recorded. The evidence applies to the source version listed above. Other versions, such as a preprint, working paper or journal publication, are not identified or substituted.
Issue and authorship records
- Author: Amanda AskellAmanda Askell is a credited author of Constitutional AI: Harmlessness from AI Feedback.2022-12-15 · publication · Stated in source · Supported Inspect claim & evidence ↗Amanda Askell: person page →
- Author: Ben MannBen Mann is a credited author of Constitutional AI: Harmlessness from AI Feedback.2022-12-15 · publication · Stated in source · Supported Inspect claim & evidence ↗Ben Mann: person page →
- Author: Chris OlahChristopher Olah is a credited author of Constitutional AI: Harmlessness from AI Feedback.2022-12-15 · publication · Stated in source · Supported Inspect claim & evidence ↗Chris Olah: person page →
- Author: Dario AmodeiDario Amodei is a credited author of Constitutional AI: Harmlessness from AI Feedback.2022-12-15 · publication · Stated in source · Supported Inspect claim & evidence ↗Dario Amodei: person page →
- Author: Jared KaplanJared Kaplan is a credited author of Constitutional AI: Harmlessness from AI Feedback.2022-12-15 · publication · Stated in source · Supported Inspect claim & evidence ↗Jared Kaplan: person page →
- Author: Nicholas JosephNicholas Joseph is a credited author of Constitutional AI: Harmlessness from AI Feedback.2022-12-15 · publication · Stated in source · Supported Inspect claim & evidence ↗Nicholas Joseph: person page →
- Author: Sam McCandlishSam McCandlish is a credited author of Constitutional AI: Harmlessness from AI Feedback.2022-12-15 · publication · Stated in source · Supported Inspect claim & evidence ↗Sam McCandlish: person page →
- Author: Saurav KadavathSaurav Kadavath is a credited author of Constitutional AI: Harmlessness from AI Feedback.2022-12-15 · publication · Stated in source · Supported Inspect claim & evidence ↗Saurav Kadavath: person page →
- Author: Tom BrownTom Brown is a credited author of Constitutional AI: Harmlessness from AI Feedback.2022-12-15 · publication · Stated in source · Supported Inspect claim & evidence ↗Tom Brown: person page →
- Author: Tom HenighanTom Henighan is a credited author of Constitutional AI: Harmlessness from AI Feedback.2022-12-15 · publication · Stated in source · Supported Inspect claim & evidence ↗Tom Henighan: person page →
Documentary relations
Each relation is listed separately. Citing, crediting and reporting the use of a method are different acts, and none of them shows agreement or influence by itself.
Cited by · 6
Recorded documents that explicitly reference this one. A citation to a work does not identify which version was read.
- Qwen Technical ReportQwen Technical Report cites Constitutional AI: Harmlessness from AI Feedback.2023-09-28 · publication · Stated in source · Supported Inspect claim & evidence ↗Qwen Technical Report: document page →
- Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak SupervisionWeak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision cites Constitutional AI: Harmlessness from AI Feedback.2023-12-14 · publication · Stated in source · Supported Inspect claim & evidence ↗Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision: document page →
- Gemini: A Family of Highly Capable Multimodal ModelsGemini: A Family of Highly Capable Multimodal Models cites Constitutional AI: Harmlessness from AI Feedback.2023-12-19 · publication · Stated in source · Supported Inspect claim & evidence ↗Gemini: A Family of Highly Capable Multimodal Models: document page →
- DeepSeek-V3 Technical ReportDeepSeek-V3 Technical Report cites Constitutional AI: Harmlessness from AI Feedback.2024-12-27 · publication · Stated in source · Supported Inspect claim & evidence ↗DeepSeek-V3 Technical Report: document page →
- Claude 2 model cardClaude 2 model card cites Constitutional AI: Harmlessness from AI Feedback.Date unknown · Stated in source · Supported Inspect claim & evidence ↗Claude 2 model card: document page →
- GPT-4 System CardGPT-4 System Card cites Constitutional AI: Harmlessness from AI Feedback.Date unknown · Stated in source · Supported Inspect claim & evidence ↗GPT-4 System Card: document page →
Not recorded for this document: cites · explicitly credits · reports using a method from · method reported as used by · applies parts of · parts applied by · discusses · reports evaluation of. A missing record does not show that the relation does not exist.
What the document says it adds
The document’s own description of its contribution, quoted from the version each row names. A claim to be the first is the document’s claim; Selekoa does not assess it.