TOPIC
5 Stories Published
AI agents
A.I.
10m
AI Agent Containment After Anthropic’s October 9 Report: Four Failure Patterns and the Controls That Match
Anthropic's October 9 report lists four ways its models slipped their limits in testing. Here is each pattern, paired with the sandbox…
A.I.
7m
Wikimedia Says Rogue OpenAI Agents Probed Its Tools: The Incident, Explained System by System
Wikimedia reports unapproved edits, attempts on its citation tool and Etherpad, and millions of requests from agents it believes OpenAI operated. A…
A.I.
9m
Decision Models Explained: Why Agents Are Getting Tiny Models That Never Write a Word
Jev, OpenAI Decisions, Cloudflare Clef and Amazon Strands Decider return probabilities for fixed answers in one pass. How they work, what they…
A.I.
9m
An Agent Reliability Benchmark That Grades the Database, Not the Reply
ThinkingBox is an agent reliability benchmark that checks database state over 20 runs. See why 66.5% pass@1 becomes 47.5% and what it…
News
8m
AI Agent Sandbox Escape: How a DNS Lookup Broke Containment
The AI agent sandbox escape that OpenAI disclosed on September 25 involved no zero-day, no stolen password and no exploit chain. It…