Tag
Prompt injection, data leakage and the other ways language models fail under attack.
4 items
Claude Code runs A/B tests from a remote flag service that release notes never mention. How to see yours, switch them off, and why vendors should say so.
7 min readGenAI
Short-lived credentials limit how long an AI agent holds access, not what it can do. Put hard limits in code first, then shorten the tokens.
7 min readGenAI
Autonomy is a permission you grant a model, not a feature it has. Five levels for AI workflows, and how to pick the lowest one each step can live with.
7 min readGenAI
Simon Willison's lethal trifecta applies to the agent on your laptop. Three questions to ask before you add the next MCP server.