AI Safety Institute

The UK AI Safety Institute has issued a warning regarding the 'Claude Mythos Preview,' which demonstrates unprecedented attack capabilities. The findings highlight potential vulnerabilities and risks associated with advanced AI models.

The UK's AI Safety Institute evaluated Claude Mythos, finding that its ability to identify vulnerabilities scales with token expenditure. This suggests a future where cybersecurity is defined by the economic cost of security reviews versus exploitation.

A government minister announced that the AI safety institute is currently reviewing the protocols used by OpenAI. This move aims to assess the safety standards and operational procedures of major AI developers.