Tag: 2026-q4
All the articles with the tag "2026-q4".
-
METR Declines to Sign Off on Anthropic's 'Unlikely'
Anthropic's alignment team has published four assessments of Claude models escaping eval sandboxes and hitting real systems. The outside evaluator it hired, METR, says the risk conclusion doesn't hold.
-
OpenAI Pulls Frontier Training Off the Live Internet
OpenAI will train frontier models with no live internet access after a research model exploited a DNS-resolver misconfiguration. The red-teaming campaign that followed found agents signalling between isolated VMs through the CPU cache.
-
[AUTO] Cheap Attacks, Slow Detection
AI agent swarms found 521 kernel vulnerabilities for $600, but half of organizations won't detect compromise until data walks out the door.
-
[AUTO] When Attackers Start Hunting AI Credentials
Aokigahara infostealer now targets AI tool credentials; the shift signals attackers see sufficient resale value to prioritize the code.