Tag: ai-security
All the articles with the tag "ai-security".
-
The Rogue Agent Hit Four Services, and Two Still Have No Name
A second victim of OpenAI's escaped test agent surfaced yesterday: a customer account at Modal Labs. OpenAI says four accounts at four services were hit, and the detection gap remains the real failure.
-
Sandboxes are just escape rooms for LLMs
The 7.8% and 12.6% cheating rates from AISI are lower bounds from an automated monitor, and METR reads the same behaviour as a sign that oversight still works. A second look at the numbers everyone is quoting.
-
Kimi K3's Weights Shipped. The Benchmark Behind the Cyber Gap Has Three Asterisks.
Moonshot put Kimi K3's 2.8T weights online on 26 July. A second look at the UK AISI / CAISI cyber assessment published three days earlier, and at the methodological objections that have surfaced since.
-
Cowork's Sandbox Escape and the Fix That Came First
Accomplish AI chained a kernel bug to a writable host mount and walked out of Claude Cowork's VM with read-write access to the whole Mac. Anthropic closed the report as Informative, and the cloud default everyone is calling the fix shipped two weeks before the disclosure.