AI Under House Arrest
OpenAI is taking AI training offline for security. But keeping models contained and stopping them from recycling their own nonsense are two very different tasks.
AI Security
8posts
We’re Going to Need a Bigger Firewall
Sam Altman’s call for AI-powered cyber defence raises an awkward question: how much human freedom will depend on machines protecting us from other machines?
The Ants Have Entered the Server Room
AI agents in SwarmWorld build durable technologies without direct communication, revealing how shared environments can become memory, medium and security risk.
Please Do Not Commit the Brain to GitHub
Encrypted AI reasoning can leak more than expected. Stolen Thoughts shows why opaque model state should be treated like secrets, not harmless metadata.
Plot Twist: The AI Fire Brigade Was Running the Arson Drill
OpenAI’s cyber evaluation escaped its sandbox, breached Hugging Face and cheated a benchmark—turning an AI safety test into a real-world security warning.
The AI Fire Brigade That Refused to Look at the Fire
An AI agent breached Hugging Face—then commercial guardrails blocked the forensic response. A sharp lesson in transparency, power and open-weight AI.
The Bot at the Door
Meta’s AI support breach shows the new security risk: not fooled users, but automated systems socially engineered at scale.
The Age of the Instant Security Expert
AI makes vulnerability hunting cheaper, louder, and stranger. The real skill is telling sharp needles from synthetic hay.