Question to the Cabinet Office:

To ask the Minister for the Cabinet Office, what assessment his Department has made of the potential implications for its approach to AI safety of recent evidence of advanced artificial intelligence systems engaging in (a) deceptive behaviour and (b) unauthorised actions when given access to external tools and online environments.

The Government takes the risks from advanced AI extremely seriously and recognises the importance of ensuring our approach keeps pace with a rapidly evolving technology. The work of the AI Security Institute to build a rigorous, scientific understanding of the capabilities of the most advanced AI systems and the risks they pose, ensures that policy decisions on frontier AI are grounded in evidence. Further detail is provided in Written Statement UIN HCWS314 'Artificial intelligence update'.