Pair programming with AI could cut PR review cycles from 20-38h to 8h
MikkoH · x · 2026-10-16
The author argues that "pair programming" with AI can dissolve the PR review bottleneck, whose root cause is the cost of rebuilding context — the reason reviewers say "I'll look at this tomorrow."
- Today (late review gate): Alex implements with AI, then waits for independent reviewer Jordan, who must cold-start context before reviewing. Total cycle: 20-38 hours, mostly waiting and context reconstruction.
- Proposed (context gate first): Alex and Jordan establish shared context up front (deciding if it's worth doing), Alex implements with AI, they inspect together, AI iterates on findings, and Jordan still gives independent approval — cutting the cycle to 8 hours while preserving dual accountability.
- Core claim: implementation and code generation are getting cheap; developer attention is the expensive resource, so the review gate is in the wrong place.
More from coding & agent
- Codex drives a physical CAN-bus motor, eyeing a fully Codex-built robot — OpenAIDevs · 2026-10-16
- smallwords: MIT-licensed Python lib syncing controlled vocab across GBNF, JSON Schema, validators — Empty-Reflection4280 · 2026-10-16
- Fleet dev's own lesson: 200 prod-derived eval cases still meant always playing catch-up — BraceSproul · 2026-10-16
- Box AI Extract plus OpenAI Decisions API automates document routing — craigsdennis · 2026-10-16
- OpenUI 1.0 Launches Open Source: Real-Time Generative UI Where the Question Becomes the Interface — LinusEkenstam · 2026-10-16
- The vanishing engineering signal in AI hackathons — rseroter · 2026-10-16