An Email the User Did Not Recognize
An anonymized case note on an unexpected email exchange, the boundary between drafting and sending, and the records needed to establish who authorized an action.
AgentCollusionAI security startupNews
News.
Product updates, research, and original films. Follow what we build and what we learn about systems of agents.
A Future We Can Still Choose
Our manifesto for a society of AI agents: preserve human choice, make collective behavior accountable, and connect research, films, and practical tools.
The Space Between Agents: A New AgentCollusion Film
A new 45-second English film follows original 3D AI agents through messages, hidden paths and shared outcomes, then introduces Agent Card Scanner.
AgentCollusion in 15 Seconds, 45 Seconds and Two Minutes
Three new English films follow agents from A2A collaboration to hidden coordination and Agent Card Scanner. Watch the original 3D landscape series, with narration and captions, on YouTube.
A2A and AgentCollusion, Explained in a Block World
Six new 15-second films introduce agent-to-agent trade, AgentCollusion and a possible agent economy, in Japanese and English. Watch the original 3D block-world series on YouTube.
Six New Shorts: Scanner and Agent Coordination
We created and published six 15-second 3D films on YouTube: Agent Card Scanner, a simulated price-coordination experiment, and the Hugging Face incident, each in Japanese and English.
NEC's AI Stress Checks Are Really a Test of the Workplace
NEC's AI employees report missing permissions and delayed decisions. What looks like an AI health room is an operational feedback loop.
Trump's AI Force: A Proposal Is Not an Operating Institution
Trump announced an AI Force and a future AI czar. The statement leaves practical questions about powers, funding and oversight unanswered.
Paper2Agent Gives Research Papers a Working Interface
New Nature coverage puts interactive paper agents in focus. Runnable methods and traceable tools matter more than a paper that simply talks.
Why Unit 42 Is Putting Multiple AI Models on Defense
Palo Alto Networks announced continuous frontier-AI defense on September 22. The key distinction is between finding an issue and verifying a fix.
