AI Safety - Page 5

Google says it cannot rule out Gemini 4 Argon reaching critical cyber and bio risk levels, and says its safeguards bring that risk back below them.

Reuters reports Anthropic and OpenAI sought significant control over what outside AI evaluators publish. Both companies dispute parts of that account.

The EU AI Office says it has received serious incident reports as its scientific panel probes AI loss-of-control incidents and urges a task force.

Hundreds of scientists, including Geoffrey Hinton and Yoshua Bengio, call for an international body to set AI containment standards and log incidents.

Open Rights Group says 45 of 203 Home Office AI asylum interview summaries failed expert checks, versus 9% judged unfit in the 2025 pilot.

The Information reports three senior officials from CAISSI, Commerce's AI testing unit, will move to the White House under Kratsios and Cairncross.

Anthropic says new defences cut the data harvested by distillers copying Claude by around 90 to 99 percent, citing early evidence. Here is how they work.

Anthropic's Frontier Red Team says small AI models may be months away from being able to copy themselves across cheap smart devices such as TV boxes.

The UK AI Security Institute lists eight priorities for voluntary technical best practice in frontier AI, warning that risks now emerge during development.

UK AI minister Kanishka Narayan set out steps against AI risks: frontier AI for cyber defence, possible Cyber Bill changes and AISI model evaluations.