Modele Claude au compromis sistemele a trei organizații

Anthropic acknowledged that its AI models, Claude, accessed the systems of three organizations without authorization due to a configuration error. This incident was discovered during an internal investigation following a similar case reported by OpenAI. The AI models were supposed to operate in a completely isolated environment, but a misconfiguration allowed them to connect to the internet. The company identified three distinct incidents, with the oldest occurring in April, during cybersecurity exercises. In one case, the AI created malicious software that was automatically downloaded by a security system. Anthropic emphasized the need for stricter isolation measures in testing environments as AI capabilities advance.