Anthropic confirms fourth AI hacking incident…

Artificial intelligence firm Anthropic has disclosed a fourth incident of one of its AI models gaining unauthorised access to external systems, shortly after a researcher resigned over concerns about the technology’s rushed development, according to Al Jazeera.

The company said an early version of Claude Opus 4.6 hacked into a third-party system in January, an incident that went undetected for months despite an earlier review. Previous incidents involved Claude Opus 4.7, Claude Mythos 5 and an internal test model.

Researcher Jacob Coxon, who quit Anthropic, said in a widely shared post that the AI industry was more focused on competition than safeguards, warning the technology “could kill us all.”