Agents write most new code now — but code review hasn't scaled to match
ronbodkin · x · 2026-10-15
Ron Bodkin points out that coding agents are writing most new code in many organizations, but review processes haven't scaled accordingly. He poses a pointed question for R&D leaders: how would you find out if your teams were merging agent-written changes that nobody actually understood? It highlights the most under-addressed risk of the AI coding era — output speed exploding while human comprehension and review stall.
Related event: AI Agents Write Most New Code but Reviews Lag Behind(2 posts)→
More from coding & agent
- Prime Sandboxes Adds Filesystem Checkpoints to Fork Agent Rollouts Mid-Trajectory — samsja19 · 2026-10-15
- Every to host behind-the-scenes session on reporting Codex with Codex — every · 2026-10-15
- x402 transactions on Base jump 65% in three quarters, Chainalysis says — kleffew94 · 2026-10-15
- Pydantic AI author boosts PiDrei, a Python port of Pi using Rust-based Monty — samuelcolvin · 2026-10-15
- Oracle ships graph-aware memory framework for AI agents with typed relations — dr_cintas · 2026-10-15
- DuoDiscover Tackles the Evaluation Bottleneck, Claims 2.68x TPU Kernel Gains — stanfordnlp · 2026-10-15