An engineer's recipe for AI self-improvement: scheduled MCP automations that fix the codebase, not bugs
DanielLockyer · x · 2026-09-13
Daniel Lockyer describes his version of "AI recursive self-improvement": scheduled automations with MCP access that continuously inspect errors, traces, and logs, then ship improvements to the codebase so the whole system gets faster.
The key, he argues, is not fixing individual bugs but operating at the meta level — finding the small number of high-leverage changes. Examples: attaching user IDs to errors for easier bug reproduction, or instrumenting parts of the code for performance — making future bugs trivial to fix.
More from coding & agent
- Building a hallucination detector taught us "hallucination" isn't one category: partition, don't boolean — Top-Shopping539 · 2026-09-13
- Fulmar open-sources a native macOS wrapper for the DeepSeek agent harness — absolutefunnyguy · 2026-09-13
- AFK Pilot Lets You Steer Grok, Codex and Claude Code from Any Browser — PawelHuryn · 2026-09-13
- AI Engineer Learning Path: Build First, Then Go Deep Where You Get Stuck — ashishllm · 2026-09-13
- Forma: Open-Source AI Tool Generates DevExpress Report Layouts from Images and PDFs — waqarsyd · 2026-09-13
- 15 days, 50 capabilities: dev turns Hermes Agent into a personal operating layer — Teknium · 2026-09-13