Your AI agent will pick the hackable codebase — and quietly reshape your architecture
tensafefrogs · hn · 2026-11-16
In a blog post, Geoff Stearns argues that when given multiple codebases or systems to work with, AI agents gravitate toward the 'hackable' one — the loosest, easiest-to-modify structure — rather than the most disciplined option. Drawing on his own experience running agents against real projects, he explores how this bias can quietly steer engineering decisions if teams don't constrain it.
More from coding & agent
- KubeCon's big theme is inference: a full-stack breakdown from DRA GPU slicing to vLLM and llm-d — AccBalanced · 2026-11-16
- Five red teamers, same AI tools, five wildly different results — rez0__ · 2026-11-16
- Swyx on AI Engineer's three themes: software factories, System 1 models, ambition — thursdai_pod · 2026-11-16
- Hiker replaced a $60/yr app with a self-built clone: 12 minutes, $0.62 in API costs via Hermes Agent — Teknium · 2026-11-16
- Expose local MCP servers to ChatGPT securely via OpenAI's official tunnel — no auth or public URL needed — altryne · 2026-11-16
- Dev replicates DeepSeek's web search UI and exposes what its queries actually look like — teortaxesTex · 2026-11-16