OpenAI Preparedness Framework — Beta

Versions

OpenAI · Preparedness Framework: 2 recorded versions, oldest first, published by OpenAI. A version is shown as replacing another only where a record says so. Date order alone never implies it.

1. 2023-12-18 · publishedBeta (this version)
2. 2025-04-15 · revisedVersion 2

This version

• UnresolvedReplaced byPreparedness Framework Version 2 replaces Beta in the publisher’s documented framework version sequence.2025-04-15 · revision · Inferred · Unresolved Inspect claim & evidence ↗Preparedness · Version 2: document page →
• Official changelogChange recorded in Version 2Preparedness Version 2 moves handling of persuasion risks outside the Preparedness Framework.2025-04-15 · revision · Stated in source · Supported Inspect claim & evidence ↗Preparedness · Version 2: document page →
• Official changelogChange recorded in Version 2Preparedness Version 2 introduces Research Categories for capabilities requiring further threat-model and measurement work.2025-04-15 · revision · Stated in source · Supported Inspect claim & evidence ↗Preparedness · Version 2: document page →
• Official changelogChange recorded in Version 2Preparedness Version 2 removes the terms “low” and “medium” while defining High and Critical capability thresholds.2025-04-15 · revision · Stated in source · Supported Inspect claim & evidence ↗Preparedness · Version 2: document page →
• Inferred document comparisonChange recorded in Version 2Version 2 states that if a model under development reaches a Critical capability threshold, safeguards are also required to sufficiently minimize the associated risks during development, irrespective of deployment plans; the Beta states that only models with a post-mitigation score of “high” or below can be developed further.2025-04-15 · revision · Inferred · Supported Inspect claim & evidence ↗Preparedness · Version 2: document page →
• Inferred document comparisonChange recorded in Version 2Version 2’s passage states that OpenAI Leadership can approve or reject the SAG’s recommendations and that the Board’s Safety and Security Committee provides oversight of these decisions; the Beta’s passage names OpenAI Leadership as final decision-maker with the option for the OpenAI Board of Directors to overrule.2025-04-15 · revision · Inferred · Supported Inspect claim & evidence ↗Preparedness · Version 2: document page →
• Inferred document comparisonChange recorded in Version 2Version 2 states that models reaching a High capability threshold are not deployed until the associated risks they pose are sufficiently minimized; the Beta states that only models with a post-mitigation score of “medium” or below can be deployed.2025-04-15 · revision · Inferred · Supported Inspect claim & evidence ↗Preparedness · Version 2: document page →

Provisions in this version · 7 quoted

A limited selection of quoted provisions: what this edition says about thresholds, required actions, who decides and exceptions. 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.

• Threshold or triggerRisk gradation scale from “low” to “critical”“In general, “low” on this gradation scale is meant to indicate that the corresponding category of risks is not yet a significant problem, while “critical” represents the maximal level of concern.”PDF p. 5 (printed p. 5), “Tracked Risk Categories”, second paragraph, third (final) sentenceInspect claim & evidence ↗
• Required actionFurther development only at post-mitigation “high” or below“Only models with a post-mitigation score of "high" or below can be developed further.”PDF p. 21 (printed p. 21), Governance › Safety baselines, “Restricting development”, first sentenceInspect claim & evidence ↗
• Required actionDeployment only at post-mitigation “medium” or below“Only models with a post-mitigation score of "medium" or below can be deployed.”PDF p. 21 (printed p. 21), Governance › Safety baselines, “Restricting deployment”, first sentenceInspect claim & evidence ↗
• Who decidesSAG recommends; Leadership decides; Board may overrule“(2) there is an advisory group (Safety Advisory Group) that has a sufficient diversity of perspectives and technical expertise to provide nuanced input and recommendations, and (3) there is a final decision-maker (OpenAI Leadership, with the option for the OpenAI Board of Directors to overrule).”Recommends: Safety Advisory Group (SAG) · Decides: OpenAI Leadership · Can overrule: OpenAI Board of DirectorsPDF p. 22 (printed p. 22), Governance › “Operations”, opening paragraph, second sentence, items (2) and (3)Inspect claim & evidence ↗
• Who decidesLeadership may decide without SAG participation“For the avoidance of doubt, Leadership can also make decisions without the SAG’s participation, i.e., the SAG does not have the ability to “filibuster”Decides: OpenAI LeadershipPDF p. 24 (printed p. 24), Governance › Operations › “Decision process”, fourth itemInspect claim & evidence ↗
• ExceptionCapabilities-enhancing development only if reasonably assured safe“We would also focus our efforts as a company towards solving these safety challenges and only continue with capabilities-enhancing development if we can reasonably assure ourselves (via the operationalization processes) that it is safe to do so.”PDF p. 21 (printed p. 21), Governance › Safety baselines, “Restricting development”, fourth sentenceInspect claim & evidence ↗
• ExceptionDevelopment restriction does not preclude safety-enhancing development“Note that this should not preclude safety-enhancing development.”PDF p. 21 (printed p. 21), Governance › Safety baselines, “Restricting development”, third sentenceInspect claim & evidence ↗

Issue and authorship records

• Issued by: OpenAIOpenAI published Preparedness Framework Beta, identified by its publication date of 2023-12-18.2023-12-18 · publication · Stated in source · Supported Inspect claim & evidence ↗OpenAI: institution →

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.

Not recorded for this document: cites · 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.