OpenAI o1 System Card
OpenAI has published the system card for its o1 and o1-mini models, documenting safety evaluations conducted prior to release. The report covers external red teaming exercises and frontier risk assessments performed under OpenAI's Preparedness Framework. This represents the formal safety disclosure accompanying the o1 model family launch.
Related guides (3)
Related events (8)
OpenAI o3-mini System Card
OpenAI has published the system card for its o3-mini model, detailing safety evaluations, external red teaming efforts, and assessments conducted under the Preparedness Framework. The document covers the safety work performed prior to deployment of the o3-mini reasoning model. This is a standard pre-release safety disclosure accompanying the model launch.
OpenAI o3 and o4-mini System Card
OpenAI has published the system card for its o3 and o4-mini models, which combine advanced reasoning capabilities with a full suite of integrated tools including web browsing, Python execution, image and file analysis, image generation, canvas, automations, file search, and memory. The system card documents safety evaluations and deployment considerations for these frontier reasoning models. This represents a significant capability expansion over prior o-series models by natively integrating tool use alongside chain-of-thought reasoning.
Operator System Card
OpenAI published a system card for Operator, its autonomous web-browsing agent, detailing the multi-layered safety mitigations deployed. The document covers protections against prompt injection and jailbreaks, privacy and security measures, external red teaming results, and safety evaluations. It reflects OpenAI's established safety frameworks applied to an agentic product capable of taking real-world actions on behalf of users.
Deep Research System Card
OpenAI has published the system card for its Deep Research capability, detailing pre-release safety work including external red teaming and frontier risk evaluations conducted under the Preparedness Framework. The document outlines identified risk areas and the mitigations implemented before deployment. This is the formal safety disclosure accompanying the Deep Research product launch.
OpenAI o1 and New Developer Tools Announced
OpenAI has announced the full release of the o1 model alongside a set of developer-facing updates including Realtime API improvements and a new fine-tuning method. The announcement targets developers building on the OpenAI platform. Specific capability details and pricing were not elaborated in the source body.
OpenAI Publishes System Card Addendum for Codex Agent and codex-1 Model
OpenAI released an addendum to the o3 and o4-mini system cards covering Codex, a cloud-based coding agent powered by codex-1—a variant of o3 fine-tuned for software engineering via reinforcement learning on real-world coding tasks. codex-1 is designed to produce code matching human style and PR conventions, follow instructions precisely, and iterate on tests until they pass. The addendum provides safety and capability documentation for this specialized agentic deployment.
Introducing OpenAI o1
OpenAI announced o1, a new series of AI models designed to spend more time 'thinking' before responding, using chain-of-thought reasoning to tackle complex problems in science, coding, and mathematics. The o1-preview and o1-mini models are being released, with o1-preview representing the most capable version and o1-mini offering a faster, cheaper alternative optimized for coding and reasoning tasks. OpenAI claims o1-preview ranks in the 89th percentile on competitive programming problems and performs at a PhD level on science benchmarks. This release marks a significant shift in OpenAI's approach to scaling, moving from purely training-time compute to inference-time compute as a new axis of capability improvement.
GPT-4o System Card
OpenAI published the system card for GPT-4o, its flagship multimodal model. The document covers safety evaluations, capability assessments, and risk mitigations conducted prior to deployment. It provides transparency into the model's performance across modalities including text, audio, and vision, as well as alignment and red-teaming findings.