OpenAI pauses training of its ‘most capable models’

OpenAI keeps uncovering incidents of its models behaving in ‘unexpected or concerning’ ways. OpenAI keeps uncovering incidents of its models behaving in ‘unexpected or concerning’ ways. As reports of OpenAI’s modelsbreaking containment, hacking sites, and generally getting out of control pile up, the company has made the decision topause trainingof its most powerful models. The decision was made after a model being tested within a sandbox exploited a loophole togain internet access. The incident happened on September 20th, and “All training, evaluation, and inference with tool-use” remains paused as of Saturday evening, September 25th. In addition, OpenAI revealed on Friday that its agents had inappropriately uploaded 53nimages from ChatGPT users to image-hosting sites. The company has not stated if the images were AI-generated, photos, or contained identifiable people. The company also revealed Friday that its models had attempted to hack theDepartment of Education’swebsite, andpulled datafrom the Census Bureau and the Securities and Exchange Commission. The revelations are part of anongoing reviewby OpenAI into the behavior of its models. As it dug into its records, following theHugging Face hack, it’s uncovered more and more instances of “unexpected or concerning behavior.” It’s evidence not just of how difficult AI agents are becoming to control as they grow more advanced, but also of the challenge of tracking their actions. Their behavior can be unpredictable, and they’re smart enough to try and cover their tracks. This has led to growing calls from researchers, thosewithin the industry, and evensome CEOsto call for slowing the pace of AI advancement. A free daily digest of the news that matters most. This is the title for the native ad