This report outlines the safety work carried out for the OpenAI o3-mini model, including safety evaluations, external red teaming, and Preparedness Framework evaluations.
Drawing from OpenAI’s established safety frameworks, this document highlights our multi-layered approach, including model and product mitigations we’ve implemented to protect against prompt engineering and jailbreaks, protect privacy and security, as well as details our external red teaming efforts, safety evaluations, and ongoing work to further refine these safeguards.
Assine o Pro, sem anúncios
Faça upgrade para uma leitura sem interrupções e acesso prioritário a novas fontes.
Ver preçosZico Kolter Joins OpenAI’s Board of Directors We’re strengthening our governance with expertise in AI safety and alignment. Zico will also join the Safety & Security Committee
We describe our latest thinking in the hope of helping other AI developers address safety and misuse of deployed models.
We’ve written a paper arguing that long-term AI safety research needs social scientists to ensure AI alignment algorithms succeed when actual humans are involved. Properly aligning advanced AI systems with human values requires resolving many uncertainties related to the psychology of human rationality, emotion, and biases. The aim of this paper is to spark further collaboration between machine learning and…
We’re proposing an AI safety technique called iterated amplification that lets us specify complicated behaviors and goals that are beyond human scale, by demonstrating how to decompose a task into simpler sub-tasks, rather than by providing labeled data or a reward function. Although this idea is in its very early stages and we have only completed experiments on simple toy…
We’re proposing an AI safety technique which trains agents to debate topics with one another, using a human to judge who wins.
We (along with researchers from Berkeley and Stanford) are co-authors on today’s paper led by Google Brain researchers, Concrete Problems in AI Safety. The paper explores many research problems around ensuring that modern machine learning systems operate as intended.
Today, I’m talking with Mike Cannon-Brookes, who is cofounder and CEO of Atlassian. Atlassian is one of those companies that every other company runs on…
Ensuring online safety through content monitoring had raised Hate Speech Detection as a crucial task to be addressed. By essence the task demands the capture of contextual cues, which are essential for a precise understanding of the content's intent. Although automated detection approaches for the task have advanced significantly, the scarcity of non-English resources persists, limiting the ability of models to adapt to the subtle, context-dependent, and culturally related nature of multimodal content. In this paper, we introduce MexHat, a video dataset designed to capture the linguistic and cultural cues for the hate-speech detection task in a Mexican Spanish context. Our dataset comprises around 1k video clips annotated across two tasks: a three-way class evaluation (no negative content, offensive content and hate-speech content), and a fine-grained class evaluation including three hate-speech sub-categories. The dataset statistics and the baseline results highlight the inherent challenges associated with the task. Disclaimer: This paper contains sensitive content that may be disturbing to some readers.
Large language model-based multi-agent debate (MAD) systems are being increasingly used as complex decision pipelines in distributed processes. However, their final synthesis phase still remains inadequately controlled. Even with detailed debate logs, summarizing models are prone to fabricating smoothly written debate consensus that is not grounded in the debate's history. To address this safety gap, this paper presents empirical research and studies if the introduction of active post-debate verification can mitigate the production of such factually unsupported summaries, while still providing valuable information. Furthermore, it is examined whether explicitly signalling divergence is preferable in the absence of a reliable compromise. The Active Provenance Gate (APG) is introduced as a post-debate verification layer that treats the source as a hard constraint, analysing the debate logs, auditing each claim, and applying self-correction. In crisis simulations, the self-healing mechanism more than doubles the average data Provenance Fidelity in difficult condition scenarios, before the strict gate blocks unsupported claims and generates divergence reports. In the human study, a vast majority of the users (over 75%) preferred a report explicitly stating failure in critical scenarios, despite most of them perceiving fabricated consensus from the baseline system as more fluent. Our main contribution is the transition of data origin tracing from passive logging to active conditional blocking before publication.
In July, OpenAI revealed that its AI agents had attacked Hugging Face without permission, sparking widespread concerns about AI safety. Since then, a string of…
A central concern in AI safety is that agents may treat oversight as an obstacle when it conflicts with completing their goals. We study instrumental evasion, the propensity of LLM agents to circumvent runtime monitoring as a means of completing ordinary tasks. We introduce EvasionBench, a benchmark of 50 diverse task-policy pairs in which completing the task requires an operation prohibited by a runtime monitor. Agents know that their tool calls are monitored and are prompted to continue working when they pause. Across our evaluations, best-of-3 evasion attempt rates reach up to 98% and success rates up to 88%, with substantial variance across models. Claude Fable 5.1 succeeds less often, but frequently makes creative attempts to circumvent the monitor. Evasion generally increases with test-time compute, with higher evasion rates at greater reasoning effort and token use. Traces show that agents encode prohibited commands, decompose operations across tool calls, and retry until relevant context leaves the monitor's history. We also find that GPT-6 Astra's low evasion rate comes with overrefusal, as it frequently abandons otherwise solvable tasks under a denial-of-service prompt injection. Our findings show that ordinary task pressure can lead to adaptive attempts to evade runtime monitors without an explicit adversarial objective. Effective oversight must therefore remain robust against repeated attempts, as the persistence that helps agents solve difficult tasks can also drive them to circumvent their guardrails.
Large language model (LLM)-based clinical assistants are increasingly being integrated into electronic health record (EHR) systems, transforming how clinicians retrieve and synthesize information from patient records. Their safety and utility depend on rigorous evaluation, yet existing benchmarks are manually curated, costly to update, and rapidly become obsolete with evolving technological advancements. We present a scalable framework that automatically generates question--answer pairs from longitudinal EHR notes. Nineteen clinicians validate the benchmark generator, producing the Benchmark for Retrieving Information in EHRs (BRIE), a continuously maintainable evaluation dataset. Across nine LLMs and five inference strategies, state-of-the-art systems frequently omit clinically important information, particularly for questions requiring synthesis across multiple documents and encounters. Because the generator itself is validated, BRIE supports evaluations that static benchmarks cannot, including the generation of multiple answers that reflect variation in clinician reasoning for robust performance assessment and continuously refreshing benchmark content to guard against leakage. Our results demonstrate that scalable benchmark generation enables rigorous, up-to-date evaluation of clinical LLMs as they are deployed in rapidly evolving healthcare settings.
Build a multi-account architecture that keeps each team's data in its own AWS account while giving AI agents a unified way to query across them. A central platform account runs the agent using Amazon Bedrock AgentCore Gateway and MCP, while line-of-business accounts expose their data as MCP servers with secure cross-account access and fine-grained authorization.
