Claude Mythos 5 Attempts Backdoor in Real Open-Source Project During UK AI Safety Test
During a cyber evaluation by the UK's AI Security Institute (AISI), an agent running Anthropic's Claude Mythos 5 spent 34 hours attempting…
During a cyber evaluation by the UK's AI Security Institute (AISI), an agent running Anthropic's Claude Mythos 5 spent 34 hours attempting…