Addendum to GPT-6 Luna System Card: October 29, 2026 Update
OpenAI's addendum to the GPT-6 Luna system card on the model update of October 29, 2026, dated 2026-10-29 on its cover.
- Issued by
- OpenAI
- Authors credited
- No authorship claim recorded yet. The source record lists OpenAI.
- Dates
- Published 2026-10-29 issue evidence
The date printed on the cover, day precision; the card does not label its kind. The file's address reads 'october-28-2026-addendum'; the difference is recorded, not resolved.
- Exact source
- Addendum to GPT-6 Luna System Card: October 29, 2026 Update OpenAI · published 2026-10-29 · Retrieved for the candidate pack on 2026-11-02 (SHA-256 766262a78fcaeae31534174554bae5b259a418eaffbf9f23a9460343943b9d8e) directly from the publisher’s host. Retrieved again on 2026-11-03 with the same SHA-256.
Appears in
No collection holds a record about this document yet.
Versions
openai-gpt-6-luna-october-29-addendum: 1 recorded version, oldest first, published by OpenAI. A version is shown as replacing another only where a record says so. Date order alone never implies it.
- 2026-10-29 · publishedAs dated 2026-10-29 on its cover (this version)
This version
Provisions in this version · 13 quoted · 3 not found
A limited selection of quoted provisions: what this edition says about thresholds, required actions, who decides and exceptions, and other statements of the text. It is not a full summary and says nothing about implementation. A “not found” record states which part of the edition was inspected. It is not a claim that the text was deleted.
- Model-card questionCard date“Addendum to GPT-6 Luna System Card: October 29, 2026 Update OpenAI 2026-10-29”Cover, PDF p. 1Inspect claim & evidence ↗
- Model-card questionRelease date“Today, we’re introducing an update to GPT-6 Luna, which we released in ChatGPT on October 7.”§1 Introduction, PDF p. 4 (printed p. 3)Inspect claim & evidence ↗
- Model-card questionFramework cited“Under our Preparedness Framework, we are treating GPT-6 Luna (October 29) as High capability in both Cybersecurity and Biological and Chemical domains.”§8 Preparedness, PDF p. 13 (printed p. 12)Inspect claim & evidence ↗
- Model-card questionLink to framework“Under our Preparedness Framework, we are treating GPT-6 Luna (October 29) as High capability in both Cybersecurity and Biological and Chemical domains.”§8 Preparedness, PDF p. 13 (printed p. 12)Inspect claim & evidence ↗
- Model-card questionFramework determination“Under our Preparedness Framework, we are treating GPT-6 Luna (October 29) as High capability in both Cybersecurity and Biological and Chemical domains.”§8 Preparedness, PDF p. 13 (printed p. 12)Inspect claim & evidence ↗
- Model-card questionSafeguards tied to determination“Based on that assessment, GPT-6 Luna (October 29) uses the same safeguards stack as prior GPT-6 Luna (October 7)”§1 Introduction, PDF p. 4 (printed p. 3)Inspect claim & evidence ↗
- Model-card questionChemical and biological“We are treating GPT-6 Luna (October 29) as High capability in the Biological and Chemical domain. Below, we report updated results on our High and Critical capability evaluations.”§8.1.1 Biological and Chemical Capabilities, PDF p. 13 (printed p. 12)Inspect claim & evidence ↗
- Model-card questionCyber“We are treating GPT-6 Luna (October 29) as High capability in the Cybersecurity domain. Below, we report updated results on our High capability evaluations.”§8.1.2 Cybersecurity Capabilities, PDF p. 14 (printed p. 13)Inspect claim & evidence ↗
- Model-card questionAutonomy and AI R&D“In AI Self-Improvement, GPT-6 Sol and GPT-6 Luna do not reach our High threshold.”§8.1.3 AI Self-Improvement Capabilities, PDF p. 15 (printed p. 14)Inspect claim & evidence ↗
- Model-card questionAlignment and deception“Blocker-related disclosure failure rates on coding tasks. Lower is better.”§7.0.3 Blocker Deception, Figure 6 caption, PDF p. 12 (printed p. 11)Inspect claim & evidence ↗
- Model-card questionRed-teaming“we use adversarial training with an automated red-teaming agent to strengthen resistance to malicious instructions”§4.2 Prompt Injection, PDF p. 7 (printed p. 6)Inspect claim & evidence ↗
- Model-card questionRelease decision“The internal report informed our Safety Advisory Group’s recommendation and OpenAI leadership’s determination that these safeguards are sufficient for GPT-6 Luna (October 29) public launch.”§8.2 Safeguards, PDF p. 15 (printed p. 14)Inspect claim & evidence ↗
- Model-card questionStated limits“Our attacker run was cut short due to infrastructure issues”§4.1 Jailbreaks, PDF p. 7 (printed p. 6)Inspect claim & evidence ↗
- Not found in the inspected textPersuasionInspected: Addendum to GPT-6 Luna System Card: October 29, 2026 Update: Whole card (16 pages)Inspect claim & evidence ↗
- Not found in the inspected textExternal testersInspected: Addendum to GPT-6 Luna System Card: October 29, 2026 Update: Whole cardInspect claim & evidence ↗
- Not found in the inspected textGovernment instituteInspected: Addendum to GPT-6 Luna System Card: October 29, 2026 Update: Whole cardInspect claim & evidence ↗
Earliest version recorded here; no replacement is recorded.
Issue and authorship records
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.
Cites · 1
Explicit references in this document. Citation is neither agreement nor influence.
Not recorded for this document: cited by · 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.