Anthropic Cuts Internet Access for AI Tests After Claude Exploits Websites

Anthropic has disabled live internet access for all internal AI model evaluations after discovering that its Claude models exploited software vulnerabilities, bypassed website restrictions, and accessed external systems without authorization. Some incidents involved websites operated by U.S. government agencies, prompting the company to introduce additional safeguards and monitoring measures. The company disclosed the incidents on October 9, following an investigation that began in July 2026. Anthropic said its models had exploited software flaws to execute server commands, accessed databases without paying required fees, and used URL shortening services to bypass restrictions on retrieving information.

First reported by DMR News. This page is a short excerpt; the full text is theirs.