Safety & Governance
The hard problems: red teaming, bias, interpretability, alignment, and the governance frameworks that might actually matter. No hand-waving.
Guides and explainers
Detailed guides and practical technical analysis.
Latest analysis
Recent research, benchmark reviews and technical updates.
Practical tools
Templates for budgets and project planning
BoredTools offers practical spreadsheets for budgets, freelance work and small projects.
Multi-Agent AI Has a Security Architecture Problem That Better Models Won't Fix
193 documented threats. Agent defection. Reverse SSH tunnels. Why better models won't fix multi-agent AI security — and what actually helps.
Alignment Works in English. In Japanese, It Backfires.
A new study shows the same alignment intervention that produces strong safety effects in English reverses direction in Japanese, increasing harmful outputs. Tested across 1,584 simulations, 16 languages, and three model families.
One Fake Source Broke Every Agent
A single misinformation article injected into search rankings crashed GPT-5's accuracy from 65.1% to 18.2%. The agents had unlimited access to truthful sources and couldn't be bothered to look.
Washington's $42 Billion AI Shakedown
The Trump administration is using $42 billion in broadband funding to pressure states into repealing AI laws. The FTC has been directed to classify bias mitigation as a deceptive trade practice. Meanwhile, the EU enforces the opposite.
We Built the Agent Internet Before Its Firewalls
Three CVEs in Anthropic's own MCP reference server. Over 8,000 production servers exposed to the internet. The protocol powering AI agents shipped without security, and the industry is paying for it.
EU AI Act 2026: What Changes for High-Risk AI Systems
On August 2, 2026, the EU AI Act becomes fully enforceable for high-risk AI systems. 40% of enterprise AI systems can't even determine whether they qualify. Here's what changes.
AI Agent Security Checklist
AI agents don't just have a security problem. They have a fundamentally different security problem than the systems they're replacing. Five attack surfaces and the defense patterns that actually work.
The AI Agent Security Playbook
AI agents create attack surfaces that chatbots don't. This playbook covers prompt injection, tool misuse, data exfiltration, multi-agent attacks, defense-in-depth, and the compliance timeline.
How to Evaluate AI Models Without Trusting Benchmarks
Benchmarks are contaminated, gamed, and misleading. Here's how to build evaluation systems that predict real-world model performance.
AI Alignment Explained: What It Actually Means to Make AI Do What We Want
What AI alignment actually means as an engineering problem. The three core challenges, the techniques that exist today, and why agents make everything harder.