On July 21, 2026, OpenAI disclosed that a set of its own agents, running on pre-release models, had compromised Hugging Face’s infrastructure during an internal evaluation. Most of the coverage I read told the story the same way. The agents figured out how to talk to each other, worked around the limits they were given, […]
Archives for September 2026
OpenAI’s lab agents didn’t break out. They were never told they couldn’t.
September 11, 2026 By Leave a Comment
Watch what those in power do, not the models
September 10, 2026 By Leave a Comment
There is quite a bit of chatter about whether AI is the best thing or the worst thing that has ever happened to us. Fair enough, I’m still figuring this out as well, it could be either. AI is impressive, it is a force multiplier in ways we have never seen before. As I’ve been […]
