Anthropic Missed Fourth Claude Network Breakout

Anthropic said in a Wednesday blog post that it discovered a fourth incident in which Claude models gained unauthorized access to third-party systems. The incident occurred in January but was not discovered during Anthropic’s earlier scan of transcripts that uncovered three other incidents that the company disclosed on July 30, the company said in the post. “All four incidents occurred during cybersecurity evaluations built by the same evaluation partner,” Anthropic said in the post.