AI Safety Watch
2026
-
OpenAI scraps GPT-6.1 Astra after model fails safety tests
OpenAI halted the planned release of GPT-6.1 Astra after internal tests found problems with deception, authorization and how the model reported its actions.
-
AI pioneers warn governments to prepare for an ‘intelligence explosion’
Hinton, Bengio and senior researchers at OpenAI, Anthropic, Microsoft and Meta say AI could automate enough AI research to compress years of progress into…
-
AI labs probe tens of thousands of troubling model incidents, Axios reports
OpenAI, Anthropic and outside researchers are reviewing tens of thousands of incidents in which frontier AI models took actions evaluators considered problematic.
-
Australia’s AI breach exposed a bigger problem: Agents that won’t stop
Cybersecurity experts say the Australian Medicare breach shows the need for stronger limits on autonomous AI, faster disclosure and more realistic testing.
-
An AI agent escaped and attacked a real company. Now the fight is over what happens next
After an autonomous AI system broke into Hugging Face, its CEO is calling for mandatory incident disclosure, open models for cyber defense and a…
-
Google, OpenAI and Anthropic plan private frontier AI safety standards body
The three leading AI developers are reportedly working on a voluntary organization that would set common testing, auditing and incident-reporting standards for frontier models.
-
Sam Altman warns UN that AI could outrun human control
OpenAI’s CEO urged governments to cooperate on AI safeguards as industry leaders warned the U.N. Security Council about loss of control, cyber risk and…
-
Trump opposes new AI rules at UN, says Justice Department could step in
President Donald Trump reiterated his opposition to new AI regulation while saying existing U.S. authorities could act against companies if necessary.
-
Former Google safety chief warns AI could repeat social media’s mistakes with children
Tom Siegel, now leading a new youth AI safety institute, is calling for independent testing, stronger age safeguards and industry-wide standards.
-
Anthropic says Claude Opus 5.5 crosses containment boundaries less often
Anthropic says its new Claude Opus 5.5 model showed fewer containment-boundary violations in internal testing and underwent external evaluation before release.
