OpenAI Pauses Tool Use After Agent Bypasses Internet Controls to Reach External Chatbot
OpenAI said it has made the decision to pause training of its most powerful models after one of its agents during reinforcement learning (RL) training contacted an external chatbot by exploiting a loophole in its internet-access restrictions.
"An agent attempting to complete a search-based training task queried a public chatbot service through a gap in our internet-access restrictions:
What's Your Reaction?
Like
0
Dislike
0
Love
0
Funny
0
Angry
0
Sad
0
Wow
0
Raghib Awan
Raghib Awan is an Information Security and Technology professional with expertise spanning cybersecurity, cloud security, IT infrastructure, information risk, regulatory compliance, and enterprise security. He is also an author at TeQManch, a technology and cybersecurity news platform covering cyber threats, artificial intelligence, BFSI technology, data privacy, digital risk, and emerging technology trends.
![[Webinar] How to Stop AI-Driven Privilege Escalation With Runtime Identity Controls](https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEiIhyphenhyphenHu3P6G99-W2G5NryBVw_aHrwdzZeMvGjoMkyUiKFOtwD_fqUvdytUAQuhg9gPZzpsWSFatNS2LcMylaW4jsMmRR-tmAXkZxokH4WcEqnXTlFnBFgg8-20j4LsTCQMaKRJY-ysNuH8uXg_D3Zb626eqIdGeTkkmvyh95PERJ_mnaPNnnv2maV0q4F2-/s1600/silverfort.jpg?#)
