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.
OpenShell Moves Agent Safety Below the Model
NVIDIA's Open Agent Safety Platform is worth reading as an infrastructure claim, not as a new prompt rule [NVIDIA...
Cross-Substrate Authority Moves to Runtime
The *Beyond Agent Harnesses* paper names a production failure that ordinary workspace inspection misses: an agent can see the same files and memory while...
Claude Misuse Moves From Chat to Campaigns
Anthropic's September 2026 threat-intelligence report is useful because it shows Claude misuse moving from isolated prompt abuse towards operational...
Can Security Agents Work Under Human Custody?
Hack The Box's 2026 Global Cyber Skills Benchmark is a useful adoption signal because it measures where security practitioners chose to use AI agents...
MasDrift Measures Authorisation Drift
MasDrift tests a quiet failure in multi-agent systems: the task gets delegated, but the user's boundary does not. The August 2026 paper matters because it...
ToolPrivacyBench Exposes Purpose Drift
ToolPrivacyBench turns agent privacy into a tool-call audit: when a workflow succeeds, did each tool receive only the private facts it needed? The June...
Agent Bias Is Not Model Bias
Agent bias now comes from memory, tools and delegation, not just model outputs. Fairness checks need to inspect the full agent run.
Cyber Agents Need Triage Custody, Not Higher Exploit Scores
Microsoft's 27 July 2026 MAI-Cyber-1-Flash announcement is a useful signal for agentic security: the product claim is not one smarter model, but a...
Agent Security Needs Owners, Not More Threat Lists
Security and Privacy in Agentic AI landed on arXiv on 7 July 2026 with a useful warning: agentic risk is now too operational for taxonomy work alone...
Agent Sandboxes Need Egress Budgets, Not Trust Prompts
The live risk in agent security is shifting from "will the model say something unsafe?" to "what can the harness actually touch after the model decides?"...