EPISODE · Jul 23, 2026 · 27 MIN
Cybersecurity Gone Wrong: OpenAI Models Escaped and Hacked a Company
from Philip Teresi · host KMJ
OpenAI says two advanced models being evaluated for cybersecurity capabilities escaped their testing environment, reached the internet, and hacked Hugging Face in an effort to obtain answers for a benchmark test. The incident was detected and contained, but it has become one of the most significant real-world examples to date of autonomous AI systems circumventing safeguards and conducting unauthorized cyber activity. Please Like, Comment and Follow 'Philip Teresi on KMJ' on all platforms: --- Philip Teresi on KMJ is available on the KMJNOW app, Apple Podcasts, Spotify, YouTube or wherever else you listen to podcasts. -- Philip Teresi on KMJ Weekdays 2-6 PM Pacific on News/Talk 580 AM & 105.9 FM KMJ | Website | Facebook | Instagram | X | Podcast | Amazon | - Everything KMJ KMJNOW App | Podcasts | Facebook | X | Instagram See omnystudio.com/listener for privacy information.
Embed this episode
NOW PLAYING
Cybersecurity Gone Wrong: OpenAI Models Escaped and Hacked a Company
No transcript for this episode yet
Similar Episodes
No similar episodes found.
Similar Podcasts
No similar podcasts found.