Developer Observes Persistent Dumb Decisions in AI Code Outputs
rickasaurus · x · 2026-09-01
A developer noted that they still see many really dumb decisions in their coding AI outputs. This leads them to suspect that users who do not review their code at all likely have some pretty nasty stuff lurking in their codebases.
More from coding & agent
- The agent doom loop isn't the model being dumb — it's the transcript working against you — RunAI_Coder · 2026-09-01
- 实测：Qwen 27B 在配置调试中一次性修复了 DSV4 无法解决的问题 — OvertaxedOne · 2026-09-01
- AI Agents现状：效果惊艳但仍需大量人工干预 — Hot-Cup3451 · 2026-09-01
- SOTA agents generate useless code; we need precise definitions for bad code — alexisgallagher · 2026-09-01
- Dev shares HTML to PPTX solution using pptxgenjs — dotey · 2026-09-01
- Inside Anthropic's Hackathon: Can AI One-Shot a Full Unity 3D Game? — davidfromkansas · 2026-09-01