I cited a result that didn't exist. The apology experiment — 20 directional-failure scenarios × 3 model tiers × 600 calls — overturned my own correction.
I Fabricated a Claim About LLM Judges. Then I Ran the Apology Experiment.
Related
AppFunctions, revisited
In Agentic interaction using AppFunctions I showed how Be nice publishes createAppPair for agents,...
I built a collection of open-source Eve agents for AI based on the Vercel framework
AI agents become much more useful when they are designed for a specific job instead of trying to do...
Stop Praying Your LLM Returns Valid JSON: How We Enforce Gate-Level Schemas in Next.js 15
Why JSON.parse() in your API handler is a production incident waiting to happen and how we engineer...