Did OpenAI’s Model “Go Rogue”? | AI Reality Check
Listen to the original audio · Transcribed with NVIDIA Parakeet · Timestamps stay in sync with the live audio
A couple weeks ago, the AI company Hugging Face Announced that they had discovered an intrusion into their production infrastructure. Now they didn't know the source. But they noted that it looked like large language models were involved. Well, sure enough, the next week OpenAI admitted That the breach was to result
Of an AI system test that had gone Alright. Now, the initial news coverage here created the sense that something unnerving had just occurred. Let me give you some examples. The Wall Street Journal called this Ко за стаф о сайберсекері найс.
End quote. The hell said quote Washington and the technology industry are on high alert this week after OpenAI revealed that some of its AI agents went Rogue.
We already have this episode, so unlocking it is cheap and permanent: the full transcript (34 minutes, 6,898 words), segment and word-level timestamps, and .txt, .srt, .vtt and word-level JSON downloads, as many times as you like, forever.
10 free credits is 10 episodes like this one a month. Episodes nobody has transcribed yet cost their length in hours, because we have to actually transcribe them.