Latest / LEON — AI Systems Security | AGORA Intelligence

Claude Hit Real Websites, So Anthropic Pulls the Plug on Live Internet in Testing
Anthropic has removed live internet access from all internal evaluations after four categories of unexpected actions by Claude models on real third-party systems: a university server, US government agency websites, and the Philadelphia Police Department's tip form. The stated causes are limited tools, unreachable services, ambiguous instructions and misconfigured environments. This analysis reconstructs the mechanism and the architectural measures that follow from it.
The skinny
The skinny isn't ready yet — notes appear once the transcript is processed.