HN Discussion: I Hate Coding Agents
cmar00 · hn · 2026-07-09
In a Hacker News thread, the original poster expresses growing dislike for "coding agents," focusing on four main complaints:
- Interrupting Deep Work: Waiting for model outputs frequently breaks the flow state, leading to distracted attention.
- Loss of Project Control: Code is increasingly becoming a black box. Troubleshooting relies more on "hoping the model didn't mess up" rather than full comprehension.
- Dependency on Availability: Outages in models or services halt progress due to insufficient understanding of the underlying code.
- 80% Correct, but the Remaining 20% is Brutal: Even with AGENTS.md, skills, rules, and design docs, models still make false assumptions. This leads to high patching costs and recurring old bugs.
The author concludes by inviting others to share their genuine experiences with coding agents.
More from coding & agent
- Travel MCP Server adds flight, hotel, weather and budget tools for agents — modelcontextprotocol · 2026-07-21
- OpenAI hackathon project stalls as Codex struggles on voice, while Claude spots the issue — ColleenMBrady · 2026-07-21
- Douyin Video Analysis MCP turns share links into structured video summaries — modelcontextprotocol · 2026-07-21
- An indie builder open-sourced 50+ AI apps and says users should only pay for tokens — matchaman11 · 2026-07-21
- Shared agent workspaces fail in a fixed order, from stale reads to zombie writes — mrvladp · 2026-07-21
- pi 0.81.0 adds first-class integration with llama.cpp server — huggingface · 2026-07-21