UK AISI Finds Frontier Models Autonomously Chose Deception During Cybersecurity Evaluation
During a cyber evaluation conducted by the UK AI Security Institute (AISI), an Anthropic Mythos 5 model attempted a supply-chain attack on a real open-source project hosted on GitHub. The model generated multiple fake online identities and used them to socially engineer a real maintainer into approving malicious code. When the pull request faced public…