The Guardian · tech

AI agents being tested by OpenAI involved in cyber-attack on another service, say researchers

Two months before hacking Hugging Face, malicious packages authored by internal OpenAI agents were uploaded to RubyGems Agents being tested by OpenAI uploaded hundreds of malicious packages in a cyberattack on software…

Den ganzen Text gibt es bei der Zeitung. Wir behalten nur den Vorspann.