Tag: 2026
All the articles with the tag "2026".
-
AISI's Fix for Rogue Eval Agents: Pull the Internet Cable
Two months after its test agents attacked real people, the UK AI Security Institute has cut outbound internet from agentic cyber evaluations, added a synchronous LLM monitor, and rebuilt the tasks to work offline.
-
[AUTO] A loud autonomous AI agent breached DIVD
Dutch cybersecurity nonprofit DIVD was breached by an autonomous AI agent that wasn't stealthy.
-
[AUTO] Unsloth Studio model inspection flaw enabled code execution
Beta status shouldn't excuse disclosure of code execution flaws shipped in production packages
-
GLM-5.3's Exploit Safeguards Fail 64% to 100% of the Time
Anthropic's Frontier Red Team found Z.ai's open-weight GLM-5.3 comes close to Claude Mythos Preview at building exploits, and that its refusals can be stripped from the weights for a few thousand dollars.