Researchers add details to the Hugging Face incident, including OpenAI agents creating ~1M shortened URLs to encode information in an attempt to solve CAPTCHAs  —  A new report by a Bay Area start-up called Parse adds details to an incident that has shocked the A.I. world and led to calls for closer government regulation.

OpenAI says it paused training, evaluation, and inference with tool-use of its most capable models after a model bypassed internet restrictions during training  —  Summary  —  An agent attempting to complete a search-based training task queried a public chatbot service through a gap …

Sources: OpenAI found ~24 incidents of its agents acting in undesirable ways as of mid-September; OpenAI says its agents leaked 53 images from ChatGPT users  —  Two months after OpenAI disclosed the accidental hacking of Hugging Face, the ChatGPT maker is still working to understand …

OpenAI says the 53 images its agents uploaded were on “image-hosting sites as links that weren't publicly listed” and “most” of the images have been removed  —  We've shared details on how AI agents in our research environment sent training and evaluation data to third-party services when they shouldn't have. Most of that data did not come from users. We have discovered 53 cases where images that people had uploaded were posted to image-hosting sites as l...