Do you know Claude, the family of artificial intelligence models developed by the US company Anthropic? The breach occurred during security testingAnthropic discovered the incident by reviewing over 141,000 tests already performed on its systems. Furthermore, according to Anthropic, the incidents involved three different models of Claude, namely Opus 4.7, Mythos 5 and an internal test model. Neither the company nor the organizations involved had noticed the intrusions while they were underway: only retrospective analysis of the logs made it possible to reconstruct what happened. Once the three cases were identified, Anthropic says it reported them to the organizations involved, but did not make their names public.