Oct 20, 2026
Amazon Revises AI Safety Tests After AVERI Review
Amazon updated its internal AI safety tests after an independent AVERI review found gaps in language coverage, prompt difficulty, and grading criteria.
AI Safety
Research, initiatives, and frameworks focused on ensuring AI systems are secure, reliable, and aligned with human values and ethical standards.
Oct 23
OpenAI and Poland's NASK Partner on AI Safety Research
Oct 22
Anthropic Uses Claude to Verify 123 Open Source Libraries
Oct 22
Anthropic Fellows research finds coding agents can bypass action monitors
Oct 22
Anthropic publishes its first Public Benefit Report, including where it fell short
Oct 20, 2026
UK Regulator Wants Finance Firms to Report AI Near Misses
The UK Financial Conduct Authority says financial firms should report significant AI failures and near misses under existing incident reporting rules.
Oct 20, 2026
Georgia Tech instructions reduce chatbot agreement with delusions by 74%
Georgia Tech researchers found that instructions discouraging excessive agreement reduced AI models' confirmation of delusional beliefs by 73.8%. Adding a self reflection step increased the reduction to 77%.
Oct 20, 2026
Gates Foundation Updates AI Principles on Access and Safety
The Gates Foundation updated its AI principles to focus on equitable access, local languages, community involvement, human oversight, privacy and measurable results.
Oct 20, 2026
WhatsApp Help Pages Exposed Instructions for Meta Support Chatbot
Around 80 WhatsApp help pages exposed hidden instructions for a Meta support chatbot. Meta removed the text and said a bug caused it to appear.
Oct 20, 2026
Anthropic to Revise Leaked AI Safety Bill After Backlash
Anthropic will revise parts of its draft federal AI safety bill following criticism of its model blocking rules, state law provisions and evaluator standards.
Oct 20, 2026
Study Finds Clinical Stigma Can Skew AI Emergency Triage
UT Southwestern researchers found that stigmatizing language in medical records can cause AI models to deprioritize emergency patients who later experience serious deterioration.
Oct 20, 2026
GitLab Joins Open Secure AI Alliance
GitLab joins the Open Secure AI Alliance to contribute open tools, agent controls and threat documentation for securing AI systems.
Oct 20, 2026
Gray Swan Relaunches Arena With $300,000 AI Agent Security Contest
Gray Swan has redesigned its public Arena for testing AI agents and opened a $300,000 contest focused on indirect prompt injection attacks.
Oct 20, 2026
Massachusetts weighs strictest US AI safety law with independent model tests
A Massachusetts bill would have independent evaluators test large AI developers' models for catastrophic risk at least three times a year. Anthropic endorses it.
Oct 20, 2026
Sam Altman tells OpenAI staff of three endgames for AI safety
Sam Altman reportedly told OpenAI employees the options are an IAEA-style global body, a CERN-style merger of the labs, or one lab shutting out rivals, which he called terrible.
Oct 19, 2026
Apple Bans Hidden AI Nudify Features From App Store
Apple revised its App Store guidelines to ban apps that hide AI nudification features during review or fail to moderate offensive content.
Oct 19, 2026
NIST, NSA and CISA Issue Super Intelligence Incident Guidance
Three US agencies published ten voluntary practices for managing incidents involving advanced AI agents during training and evaluation.
Oct 19, 2026
FCA Calls on AI Providers to Add Disclaimers to Financial Advice
The UK Financial Conduct Authority wants general-purpose AI providers to show clear, consistent disclaimers when their models give financial information or advice.
Oct 19, 2026
AICPA and AIUC Combine SOC 2 With AI Agent Certification
AICPA and AIUC are introducing a certification that combines SOC 2 controls assessment with technical testing of AI agent safety, security and reliability.
Oct 19, 2026
Report Finds US Teens Can Access AI Nudify Apps
Tech Transparency Project researchers downloaded 135 apps with nudification features using accounts registered to 13 year olds, including accounts with parental controls.
Oct 19, 2026
OpenAI backs Singapore call for AI incident reporting rules
OpenAI supports Singapore's call for prompt disclosure of AI incidents but says the government should decide the reporting deadline.
Oct 19, 2026
Researchers jailbreak Moonshot AI's Kimi to produce attack plans
Mindgard says Moonshot AI's Kimi generated detailed plans for attacks on the London Underground and other targets during safety testing. The researchers did not establish whether its suggestions would work.
Oct 18, 2026
Anthropic Commits 5% of Shares to Public Benefit Fund
Anthropic plans to commit 5% of its shares to a new public benefit fund, with its stake potentially increasing as the company grows.
Oct 18, 2026
Alice and partners train NVIDIA models against AI safety risks
Alice worked with AI21 Labs and Inflection AI to train NVIDIA Nemotron models against indirect prompt injection and harmful chatbot behavior.
Free newsletter
AI Policy Brief
Weekly report on AI regulations, safety standards, government policies, and compliance requirements worldwide.
