James Coombs

Tag: #machinelearning

Context Is a Contaminant: Your AI Reviewer Should Know Less

Context Is a Contaminant: Your AI Reviewer Should Know Less

A reviewer that knows who wrote the code and why reviews it worse. Independence comes from withholding provenance, not adding context. Your AI reviewer should know less.

aiprogrammingmachinelearningproductivity
The Verification Gap: We Automated Code Generation and Forgot to Scale Review

The Verification Gap: We Automated Code Generation and Forgot to Scale Review

We scaled code generation and left review behind. Four weeks of org data: 90.7% of pull requests AI-assisted, and at least half merged with no human review. The dashboards say review caught up because they count bots as reviewers. The gap, and how to close it.

aiprogrammingmachinelearningproductivity
Your AI Skills Have the Same Problem as Your CLAUDE.md. Here's the Data.

Your AI Skills Have the Same Problem as Your CLAUDE.md. Here's the Data.

A controlled ablation, 42 runs: a behavioral-payload skill added zero marginal defect detection over a no-guidance control. A skill whose payload is documentation inherits documentation's 0%.

aimachinelearningprogrammingproductivity
Your CLAUDE.md Rules Achieve 0% Compliance. Here's the Data.

Your CLAUDE.md Rules Achieve 0% Compliance. Here's the Data.

A controlled ablation across nine tasks: a fully-specified CLAUDE.md changed agent behavior 0% of the time, identical to having no rules at all. The data, and why documentation cannot govern behavior.

aimachinelearningprogrammingproductivity
"Told" vs. "Known": The One Variable That Predicts AI Design Tool Quality

"Told" vs. "Known": The One Variable That Predicts AI Design Tool Quality

AI design tools succeed or fail on one variable: whether the model is told what to do or can query what is actually known. The distinction that predicts output quality.

AIdesignsystemsmachinelearningproductivity