Latest Posts
Pinned
The Hidden Cost of LLM-as-a-Judge: When More Evaluation Means Less Value
More evals ≠ better results. Understand how excessive, generic evaluations can undermine product efficiency—and what smarter, sampled strategies look like.
Advancing AI Observability: From Metrics to Meaningful Insights
Building on our production readiness checklist, this post dives deeper into practical strategies for instrumenting and monitoring AI systems.
Stay Informed: My Top RSS Picks
Discover the RSS feeds that keep me updated and informed in the digital world.