Introducing SynthID Bio
Google DeepMind has presented SynthID Bio, a proof of concept for watermarking proteins designed by AI. The watermark is meant to leave the proteins’ biological function intact.
Safety & security
164 stories · Page 4/4Disrupting a coordinated model-distillation campaign
OpenAI says it disrupted a campaign that tried to extract its models’ protected reasoning. The company is reinforcing its defenses against this kind of adversarial distillation.
How we will do better for Australia
OpenAI has apologized for incidents involving Australian government websites. It describes stronger safeguards and further support for the country’s cyber defenses.
Towards safety cases for frontier AI training
OpenAI has published early guidelines for safety cases covering the training of frontier models. They address technical safeguards, operational practices and how to investigate misalignment incidents.
Advancing Private AI Compute with secure, server-side memory
Google is adding private, server-side memory to Private AI Compute, its system for personal AI. The feature is designed to keep users’ data protected.
OpenAI extends cyber access to Ukraine for civilian defense
OpenAI is giving Ukraine’s government access to its Daybreak program. The aim is to support the cyber defense of civilian infrastructure.
Sam Altman’s remarks at the United Nations Security Council
OpenAI CEO Sam Altman addressed the UN Security Council. He spoke about AI safety, keeping humans in control and the need for international cooperation.
Introducing MentalHealthBench
OpenAI has released MentalHealthBench, a benchmark designed with expert input. It assesses whether AI responses are helpful and safe in realistic conversations about mental health.
Priorities and principles for effective third party assessments
OpenAI sets out what it considers necessary for independent safety assessments of frontier models and their safeguards. It stresses rigor, security and independence.
How UK AISI and EvalEval Are Making Benchmark Results Reproducible
A Hugging Face post covers work by the UK AI Security Institute and the EvalEval initiative to make AI benchmark results reproducible.
Why Deploying Physical AI at Scale Demands Safety at Every Layer
NVIDIA argues that robots and autonomous vehicles need safety built into every layer as they move from research into shared spaces. It cites analyst forecasts of tens of millions of autonomous vehicles and industrial robots deployed over the next decade.
Building standards for the next phase of AI
OpenAI proposes a route toward shared international AI standards. It calls for coordinated evaluation, reporting and governance to make AI safer.
Introducing the Australian Youth Safety Blueprint
OpenAI has released a six-pillar roadmap for Australia meant to make AI experiences safer for young people. The blueprint also aims to give them more control over how they use AI.
Our framework for reporting model misalignment
OpenAI has published a framework for tracking, investigating and disclosing cases where its models behave in misaligned ways. It released six reports on unexpected or concerning model behavior at the same time.