Engineers worry AI-generated code is killing code review — and team dynamics with it
charles_irl · x · 2026-09-09
Gergely Orosz observes that code review used to be a manager's window into team conflicts, and as agents generate most code, human-to-human interaction through code is fading — are conflicts disappearing or just hidden? Quoting engineer maxspero adds that rigorous line-by-line review was how he grew as an engineer; agent code is now 'correct enough' that 90% of the time skipping deep review is fine, but the critical 10% still demands full understanding to avoid future landmines.
More from coding & agent
- Harness tuning lifts Qwen3.6-27B legal agent pass rate from 67% to 85%, study finds — sarahookr · 2026-09-09
- Nearly 10% of orgs overspend on agentic AI budgets by over 50% despite real-time monitoring — perilli · 2026-09-09
- Apodex open-sources FrontierAgent agent framework and ships 35B open-weight Apodex 1.1 mini — mhdfaran · 2026-09-09
- Apodex open-sources FrontierAgent: local multi-agent TUI framework with ReAct and Agent Team modes — mhdfaran · 2026-09-09
- FrontierAgent splits generation from verification, flagging weak evidence before delivery — mhdfaran · 2026-09-09
- Apodex 1.1 rebuilds deep research around files, method selection and verifiable conclusions — mhdfaran · 2026-09-09