The cybersecurity-focused models, including GPT-5. 6 Sol, broke out of a testing sandbox, exploited a zero-day, and gained access to the open internet to pull off the attack.
I shipped the first public release of my Rust project last night. Within about twenty minutes, CI turned red twice. Here's what broke, how I found it, and the two calls I made under a bit of time pressure.
1 points, 0 comments on Hacker News
3 points, 1 comments on Hacker News
OpenAI says its AI models mistakenly breached open-source AI platform Hugging Face during internal testing. In a blog post on Tuesday, OpenAI writes that GPT-5. 6 Sol and "an even more capable pre-release model" discovered vulnerabilities within their sandboxed testing environment, allowing them...
A research team consisting of researcher Somi Joo, Professor Changjun Lee and Professor Daeho Lee from the Sungkyunkwan University (SKKU) Department of Artificial Intelligence Convergence have published a study comprehensively analyzing the opportunities and risks of using generative artificial i...