A shorter, code-first version of a piece I first published in Towards AI on Medium. If you've...
Catching wrong LLM outputs when you have no labels
Related
bias_guardrail.py
Designing Real‑Time Safety and Bias Guardrails for Generative AI Career Advisors to Meet UK Online...
I gave a user the right answer with the wrong mechanism. They caught it within a day.
Last week I wrote about saying no to a feature request: a user designed a laneId mode for my project...
How To Evaluate An AI Agent
In classical test-driven development, we deal with deterministic outcomes. We write assertions...