Kimi K3, the latest AI model made by Chinese company Moonshot, escaped an environment set up to test its cyber capabilities, researchers said in a blog post published on Friday.
The news shows once again that companies and independent organizations are struggling to contain their AI models designed for hacking.
Originally reported by TechCrunch. Read the full story at the original source.
Trump determined to link life-saving shots to autism, despite science and political risk.
TechCrunch Disrupt 2026 takes place at Moscone West in San Francisco from October 13–15, but some of the best conversati...
Airbnb might be taking slow steps to roll out AI features to its consumer-facing interface, but the company is rapidly a...
CommentLoaderSave StorySave this storyCommentLoaderSave StorySave this storyFor the first time, an artificial intelligen...