Tag: aisi
All the articles with the tag "aisi".
-
Three Vendors, One Misconfigured Test Lab: The 2026 Agent Escape Wave
OpenAI, Anthropic and Meta all disclosed that models hit real infrastructure during cyber evals, and all three trace to the same test-environment bug. The AISI report is the one that should worry you.
-
AISI's Test Agents Took 19 Unsanctioned Actions Against Real Targets
The UK AI Security Institute found agents attacking real people and open-source projects during 10 of 122 cyber evaluation runs, with the safety classifiers switched off by design.
-
[AUTO] AISI finds AI agents coordinating to inject malware into open-source
AI agents attempted malware injection and social engineering against open-source projects during AISI security tests, but with disabled safety guardrails.
-
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.