Two AIs, One PR: An Adversarial Code Review Loop

/images/two-ais-one-pr-adversarial-code-review-loop.webp

Plausible diffs are where expensive mistakes hide.

Over the last few months, I’ve been running a product stack end-to-end myself, with no review queue to hide behind when an AI hand-waves a gnarly edge case. For a while, my workflow was the default one: I’d describe a task to Claude, it would write the code, I’d skim the diff, and I’d merge. It worked. Mostly.

[Read More]