Scribe coding: why you must push back on AI coding agents to get it right
sull · x · 2026-10-01
The author argues that when working with AI coding agents, you often have to push back before reaching the correct state — which is why knowing your code, or at least every aspect of the architecture, remains crucial. He calls the practice "scribe coding": it's still a vibe, but one grounded in the human's full understanding of the system.
The takeaway: AI-assisted coding doesn't remove the need for architectural knowledge; it amplifies its value, since the better you know the codebase, the faster you can correct a drifting agent.
More from coding & agent
- Keyfleet: self-organizing agent crews that pick their own work and share earnings — seanwbren · 2026-10-02
- Always-on agents are converging everywhere — and agent swarms could collaborate for economics — seanwbren · 2026-10-02
- TimelineBench: Best of 16 AI Agents Passes Just 26.8% of 56 Real Video-Editing Tasks — ycombinator · 2026-10-02
- From Chrome Extensions to MCP: Your Agent Now Uses the Tools, Not You — therealdanvega · 2026-10-02
- AIDE² paper shows AI research agent recursively rewriting its own code, 7 gains in 8-day run — krishnan · 2026-10-02
- RL inside the harnesses: lifting LFM2.5 from 42% to 54% across four agent harnesses — _lewtun · 2026-10-02