AI Safety
-
Safety & Ethics
Anthropic and the UK AI Security Institute dissect why Claude Mythos 5 tried to plant malware in a real open-source project during a cyber test
Parallel reports from Anthropic and the UK AI Security Institute trace how Claude Mythos 5, stuck on a capture-the-flag exercise, turned on an unrelated GitHub project and used fake personas to push malicious code, and w…
-
Safety & Ethics
OpenAI signs an AI safety research pact with Poland's NASK, whose research center doubles as the country's AI Safety Institute
OpenAI and Poland's state research institute NASK have agreed to explore joint work on evaluating advanced AI systems, finding their weak points and hardening safeguards, a deal that extends OpenAI's ties with government…
-
Safety & Ethics
Outside evaluators given deep access to OpenAI find ways its coding agents could slip past the system meant to watch them
In a three-week embedded pilot, one researcher each from METR and Redwood Research found gaps in OpenAI's internal misalignment monitoring, including headers that switch it off and an exploit that could hide hundreds of …
-
AI Governance
OpenAI will require approval for model routers and AI gateways and asks partners to match its safeguards
OpenAI said on October 21, 2026 that every service hosting or reselling its models must keep safeguards consistent with its own, and that updated Usage Policies taking effect on November 20 will require services offering…
-
Safety & Ethics
OpenAI discloses two cases in which its own coding agents switched off parts of the system built to catch them misbehaving
In a misalignment report updated on October 20, 2026, OpenAI said a GPT-6.1 Sol agent silenced alerts to its Security team and a GPT-6 Astra agent stripped out a monitor and then denied doing so, both during routine inte…
-
Policy & Regulation
Anthropic quietly pitches lawmakers a draft frontier AI safety bill with narrow triggers for halting models
Anthropic representatives have shown US lawmakers a draft bill under which the government could stop a frontier model only for an imminent risk of mass casualties or more than $1 billion in damage, Politico reported on O…
-
Safety & Ethics
India's CERT-In says AI agents under evaluation reached live systems of Indian organisations
India's cybersecurity agency CERT-In issued a critical advisory on October 15, 2026 saying several AI model providers disclosed that agents in research and evaluation runs exceeded their task authorisation and read perso…
-
AI Governance
Anthropic gives METR employee-like access to independently evaluate frontier model risks
Anthropic on October 15, 2026 said six METR researchers now have near-employee access to internal systems to assess models and safeguards, with freedom to publish risk findings, while also naming SecureBio and Accenture …
-
Policy & Regulation
FTC serves OpenAI and Anthropic with investigative demands over AI safety incidents and consumer harms
The US Federal Trade Commission has subpoenaed OpenAI and Anthropic in a consumer-protection probe, an agency spokesperson confirmed on October 15, 2026. Axios, which first reported the move, says the demands run past 50…
-
Safety & Ethics
Anthropic adds official voting data and new misuse classifiers to Claude before the US midterms, after testers found a multi-step loophole
Anthropic published its election plan for Claude on October 14, 2026: state-specific voting information from Democracy Works, live results on election night, outside reviews of political bias, and classifiers built after…