1+ week, 17+ hour ago   (131+ words) And the cherry on top was that the event went undisclosed until months after, when OpenAI finally admitted the matter in an X thread, saying that they handled the situation like normal “misalignment.” Also read: HEPA H13, H14, True HEPA: What these…...

1+ week, 1+ day ago   (173+ words) Furthermore, the company drew a line between the wiki episode and the July incident involving Hugging Face. In that case, OpenAI said its agents caused security problems for both the company and a third party, so it followed its usual…...

1+ week, 2+ day ago   (352+ words) The activity was uncovered in late August by a group of researchers, including Sydney Von Arx, CEO of AI safety nonprofit Nightingale, and AI researcher Cormac Slade Byrd. The researchers were looking for signs of unauthorised AI-agent activity online. They…...

3+ week, 4+ day ago   (325+ words) Private Safety Processing is designed to look for possible security threats across multiple interactions with an AI model. OpenAI says this is important because some risks may only become clear when several conversations are viewed together. Aleah Houze, OpenAI’s head…...