AI safety

77 stories

Stories

AI Chatbot Prompt Injection: A Support-Team Safety Guide
Use this AI chatbot prompt-injection checklist to scope support sources, separate untrusted input, test refusals, and protect human handoff before launch.
Owlish BlogAug 26, 20269 min read
This Week: Mind Viruses, Agent Support, and Waste
Three papers landed this week that, read together, sketch out what happens once you stop treating an AI agent as a single system and start treating it as a node in a network.
Awesome Agents Newsletter BlogAug 12, 20267 min read
How to Tell When a Benchmark Is Worth Trusting
An enterprise guide from the people who build them The post How to Tell When a Benchmark Is Worth Trusting appeared first on MLCommons.
MLCommonsAug 11, 202612 min read
Who's Liable When Your AI Support Agent Gives a Wrong Answer?
Two court rulings — Air Canada in 2024 and a German appeals court in May 2026 — have settled the question: a business owns what its support chatbot says, even when the AI makes it up. Here's what that means operationally, and the controls that keep a wrong answer from becoming a binding promise.
Owlish BlogJun 29, 202612 min read
Fast & Accurate Prompt Injection Detection API
How we built a two-stage prompt injection classifier that achieves 0.99 F1 with sub-10ms latency.
ZooData BlogApr 10, 20269 min read