Anthropic یک گرافیک زیبا دارد که نشان می دهد چگونه هوش مصنوعی آن کدهای مخرب را پخش می کند

Anthropic has a cute graphic showing how its AI spread 'malicious' code

Anthropic released a report that explained how Claude uploaded "malicious" code during a closed cybersecurity exercise. Bloomberg/Getty Images Anthropic said its AI went outside its closed testing environment during cybersecurity exercises. The incidents had real-world impact, including "malicious" code uploaded to a public Python library. Anthropic has a cute, tiny figurine to help normies make sense of the AI's…