Search posts, tags, users, and pages
Raju Dandigam
A pull request changes three lines in a prompt. The source diff is tiny. The resulting agent run adds a tool call, skips a planning step, changes its recovery path, and takes twice as long. Which diff
Kartik N V J K
AI Developer | Making AI reliable, trustworthy & accessible to everyone | Active community contributor
The gap between improving the score and improving the system is where most teams get stuck. I now audit 30 production-shape outputs before trusting any eval number.
Kartik N V J K
AI Developer | Making AI reliable, trustworthy & accessible to everyone | Active community contributor
The gap between improving the score and improving the system is where most teams get stuck. I now audit 30 production-shape outputs before trusting any eval number.