Devs debate: Claude still errs too much, and self-maintained software may not be the endgame
ivan_bezdomny · x · 2026-11-10
ivanbezdomny pushes back on the idea that everyone wants AI to "manage your own software": until Claude can build with fewer mistakes and better self-maintenance, it remains limited — though he admits he doesn't know if self-managed software is where most people want to end up, even as he does increasingly more of it himself.
stanyurin adds that proper upkeep of anything important takes at least half a day even when Claude makes no mistakes — a reality check on the hidden cost of vibe coding.
Related event: Devs Debate Whether AI Coding Could End the SaaS Era(2 posts)→
More from coding & agent
- Two 'fresh eye review' prompts catch AI coding mistakes after generation — doodlestein · 2026-11-10
- InstructGPT co-author's Jev harness PDF promises 200x faster, 400x cheaper coding agents — Redo · 2026-11-10
- Three coding-agent security patches ship this week: Mistral Vibe, Jan, DeepSeek Harness — alvelda · 2026-11-10
- Dev rewrote Node app in Go, asks why developer-friendly languages matter when AI writes code — rakyll · 2026-11-10
- Claude Fable 5.2 Lands in Factory: Works Through Diagnostics, Keeps Precision — matanSF · 2026-11-10
- Open-Source MCP Lets AI Agents Edit Your YC Application Directly via GraphQL — arthurcolle · 2026-11-10