Yegge: Any model will eventually build systems it can no longer maintain
jimmykoppel · x · 2026-09-02
Steve Yegge shares a lesson from AI coding agents: any model, however smart, will eventually build systems it can no longer understand or maintain if left unchecked. His agent on Fable outbuilt itself and flailed for a week; Fable 5.1 appears to fix it for now. His takeaway: keep an iron grip on system size or the codebase will run away. Jimmy Koppel followed up asking for details on what the flailing looked like.
Related event: Steve Yegge Warns AI Agents Build Systems They Can't Understand(3 posts)→
More from coding & agent
- Claude-written test harness let 31KB fake archives land on a real backup server — Grimmoner · 2026-10-18
- Open-source Tyger-S2S voice agent runs natural, interruptible conversations on a single GPU — solyarisoftware · 2026-10-18
- Matt Pocock's pre-commit hook caps agent-written files at 5,000 tokens — mattpocockuk · 2026-10-18
- Backups silently failed for 10 days: three monitoring blind spots lined up — Grimmoner · 2026-10-18
- Author Laurence Moroney: write your ugly first draft yourself, then let an LLM edit it — lmoroney · 2026-10-18
- Open-weight TYGER speech decision model makes 80ms turn-taking calls for full-duplex voice agents — solyarisoftware · 2026-10-18