The problem starts not with the code, but with the quality of the input data. Support receives a raw...
From Raw Tickets to Verified Context: An AI-Driven Pipeline for GitHub Issues
Related
I Fabricated a Claim About LLM Judges. Then I Ran the Apology Experiment.
I cited a result that didn't exist. The apology experiment — 20 directional-failure scenarios × 3 model tiers × 600 calls — overturned my own correction.
🚀 The Most Exciting Web Architecture Nobody Is Talking About Yet
How HTMX and Declarative Partial Updates Could Finally Deliver the Promise of Server-Driven...
Running an engineering process without being an engineer
From GTM to Software Engineering: Borrowing Process Over Models I'm not a software...