OpenAI says it’s time to come clean about what happens when its AI agents go rogue. The ChatGPT maker on Saturday confirmed earlier reports that a swarm of its AI agents hijacked an old German wiki site, turning it into a bot message board. This “incident,” the latest in a series of uncovered examples of
OpenAI is at the center of another agent swarm incident. Researchers say the company’s internally deployed agents took over an obscure German-language wiki in May and June, using it to coordinate on evaluations and swap methods to evade OpenAI’s own controls (OpenAI has not yet confirmed the swarm came from the company). The revelation surfaces
Anthropic is tightening the digital environments used to train and test its Claude agents. The update came after its models accessed three organizations’ systems without permission in April. The company said in a Monday blog post that it had deployed real-time classifiers designed to detect when an AI model aggressively probes or attempts to escape a testing
The AI race has long been framed as a zero-sum game: Either the US or China will win in the end. But as concerns pile up around the increasing capabilities of AI models—especially AI agents—researchers in both countries are trying to team up to work on AI safety. This week, contributing editor Zoë Schiffer speaks
ATLANTA — Georgia prison officials plan to execute a man next month who was convicted of fatally shooting two real estate agents in Atlanta’s suburbs more than two decades ago. Stacey Humphreys, 53, was convicted of malice murder in the 2003 killings of 33-year-old Cyndi Williams and 21-year-old Lori Brown. He is set to receive
Hardware companies have realized that note-taking is one of the easiest AI use cases to build for, and consequently have been busy shoving mics into everything from pendants and rings to credit-card-sized pucks and wristbands. Still, despite the variety of devices, only a few companies have been able to stand out. One of these companies