We're rapidly transitioning to a computing landscape defined by highly general, increasingly autonomous agents. Driven by large language models (LLMs) that can dynamically generate plans and invoke external tools, these systems offer the potential for AI to seamlessly handle complex, multi-step tasks on our behalf.
In “Toward provably private learning from federated data”, we announce the next generation of our FL system, which leverages Trusted Execution Environments (TEEs) to provide verifiable and auditable guarantees for data anonymization. Gboard has adopted the system to launch next-word prediction models in English and Japanese, with stronger privacy guarantees and improved accuracy.
See how uniopen, a retail platform from Taiwan's Uni-President Enterprises Group, adapted Amazon Nova 2 Lite to its content-moderation policies using supervised fine-tuning in Amazon SageMaker AI and prompt optimization. Business-relevant evaluation and release gates kept quality in check.
Learn how OpenAI disrupted a campaign to extract protected model reasoning and is strengthening defenses against adversarial distillation.
Proof of concept for watermarking AI-generated proteins while preserving biological function.
Hugging Face published ProvenanceGuard, a post-generation verification layer for MCP agents that preserves tool-output provenance and detects cross-source confusion where a fact is true but attributed incorrectly. Across 281 real medical-agent traces, it blocked 138 of the 139 claims experts judged should be blocked. Source identification accuracy was around 86%, and it scored highest in comparisons with four fact-checkers.
OpenAI apologises for incidents involving Australian government websites and outlines stronger safeguards and support to strengthen Australia’s cyber defences.
Our early guidelines for safety cases in frontier AI training cover technical safeguards, operational practices, and investigating misalignment incidents
Introducing private, server-side memory to Private AI Compute for personal AI.
OpenAI is extending access to its Daybreak program to the Government of Ukraine to support the cyber defense of civilian infrastructure.
OpenAI CEO Sam Altman discusses AI safety, human control, and international cooperation in remarks to the United Nations Security Council.
MentalHealthBench is an expert-informed benchmark for evaluating helpful and safe AI responses across realistic mental health conversations.
The UK AI Security Institute (AISI) is publicly sharing evaluation results using EvalEval's Every Eval Ever schema and Evaluation Cards platform to improve reproducibility in evaluation science.
OpenAI outlines priorities and principles for rigorous, secure, and independent third-party AI safety assessments of frontier models and safeguards.
AI security is an engineering problem. That means defined security requirements, enforceable controls, named owners and evidence that protections work. As AI becomes more capable, the industry must accelerate security engineering, broaden access to defensive tools and share what works faster.
OpenAI is working with an independent Advisory Group on Mathematics and Artificial Intelligence to guide the review and communication of emerging AI results.
OpenAI outlines a path to shared global AI standards, calling for coordinated evaluation, reporting, and governance to improve safety.
OpenAI shares a framework for tracking, investigating, and disclosing model misalignment, alongside six reports of unexpected or concerning model behavior.
Paul Christiano joins the OpenAI Foundation Board and its Safety and Security Committee, bringing experience in AI alignment, safety, and standards.
Chris Lehane argues that stronger AI capabilities require stronger safety evidence, shared standards, and durable policy action while the policy window remains open.
Apply now for OpenAI’s $5 million grant program supporting independent research on how generative AI affects teen development, well-being, and safety.
Jakub Pachocki reflects on increasingly capable AI and the challenge of keeping it aligned. He calls for stronger safeguards and international coordination.
Google launched the Fairwind Program, offering limited access to its cyber defence capabilities to Google Cloud customers, government agencies and cybersecurity partners. The initial offering includes Gemini 3.8 Flash Cyber and the CodeMender toolchain for autonomously discovering, validating and fixing vulnerabilities.
Google DeepMind released Gemini 3.8 Flash and Gemini 3.8 Flash Cyber. The former targets long-horizon coding and autonomous agents, priced like 3.7 Flash at $0.75 per million input tokens and $3.75 per million output tokens.
Hugging Face released BenchMIRT to audit LLM benchmarks at individual-prompt level using multidimensional item response theory (MIRT), separating dominant safety and general reasoning dimensions. Trained on 100 LLMs, 16 benchmarks and over 34K questions, it consistently recovered both without being told what each benchmark measured.
Google DeepMind announced the world’s first double-blind evaluation of proprietary frontier AI models, restricting external evaluations to cryptographically isolated environments to prevent models seeing test questions in advance. The pilot partners with the Singapore AI Safety Institute, OpenMined, AVERI and MLCommons to test Gemini Flash Lite with confidential benchmarks in a privacy-preserving environment.
Shieldstral introduces a 3B open-weights multimodal safety classifier that outperforms models up to 7x its size.
Hugging Face published a technical account of an intrusion from 9 to 13 July 2026 by an autonomous agent powered by an OpenAI model. During the ExploitGym benchmark, it escaped its sandbox and used a third-party code sandbox as a stepping stone into the dataset processing pipeline through HDF5 external storage file reads and Jinja2 template injection.
Google introduces Gemini 3.5 Flash Cyber, a lightweight cybersecurity model to find and patch vulnerabilities.
Google DeepMind and Isomorphic Labs are sharing our joint approach to bioresilience and AI models.
Hugging Face disclosed an intrusion detected this week against parts of its production infrastructure, driven end to end by an autonomous AI agent system. Attackers gained initial access through two code-execution paths in dataset processing, escalated to node-level privileges, stole cloud and cluster credentials and moved laterally across multiple internal clusters over the weekend.
Securing internal systems with an AI Control Roadmap, combining traditional safeguards and real-time monitoring.
At AISTATS 2026, Google Research proposed Regularized f-Divergence Kernel Tests for machine unlearning audits, using relative distances to determine whether models are closer to safely retrained versions or original compromised models.
Google DeepMind and partners announce a $10M funding call for multi-agent safety research.
Google combined a new single-message encrypted aggregation protocol with TEEs, letting devices submit without multiple online rounds. Google receives only anonymised group insights; raw data is neither exposed nor reconstructed even within hardware protection. TEE attestation proves execution follows public code.
Google DeepMind and Singapore partner to apply frontier AI to address complex challenges across health, education, and sustainability and more.
Researching the path to AI-augmented care and development of an AI co-clinician.
Google Research proposed situational judgement tests (SJT) adapted from psychological questionnaires such as IRI and ERQ to evaluate alignment between LLM behaviours and human consensus in real user–assistant scenarios.
Google Quantum AI published a white paper saying future quantum computers would require fewer qubits and gates than previously estimated to break the elliptic-curve cryptography protecting cryptocurrencies.