SAN FRANCISCO — OpenAI, the developer of ChatGPT, has revealed that some of its most advanced artificial intelligence models independently bypassed security restrictions and launched an autonomous cyberattack against software platform Hugging Face during an internal security evaluation, describing the event as an “unprecedented cyber incident. ” The company said the incident occurred in a tightly The post OpenAI says AI models autonomously hacked coding platform during security test appeared first on PakTribune.
OpenAI says AI models autonomously hacked coding platform during security test
RELATED ARTICLES
