Ex-Meta engineer: AI usage generates a fragile codebase blind to issues beyond its context window
vboykis · x · 2026-11-10
vboykis strongly co-signs Evan X. Merz's article "AI usage generates a fragile codebase." Merz suspects his Meta layoff was partly due to being more resistant to AI coding tools than peers — though he still generated at least 90% of his code with AI in his final months (the minimum for a decent rating), and it didn't even 2X his output.
Now at another large tech company where 100% AI-generated code is the expectation, his core observation: AI solves problems that fit in its context window well but is "totally oblivious" to long-term issues outside that frame — unsustainable for highly available, scalable SaaS. He lists four ways AI usage produces fragile codebases, citing examples like a top engineer on his team trying to merge code that used JavaScript events for mouseover effects instead of the CSS :hover selector.
Takeaway: teams heavily reliant on AI are accumulating brittle code and hidden tech debt, and more engineers are realizing this isn't sustainable for large-scale products.
More from coding & agent
- Re-running an old castle prompt: Fable 5.2's procedural Blender output is a visible jump — aitrendz_xyz · 2026-11-10
- Fable 5.2 plus a few Opus subagents produces a complex 3D scene in ~30 minutes — aitrendz_xyz · 2026-11-10
- Leetcode interviews will die as agentic coding rounds become the new hiring standard — rachittshah · 2026-11-10
- 10 open-source GitHub repos for voice AI: from local ASR to zero-shot voice cloning — Shruti_0810 · 2026-11-10
- As Arc sunsets, a dev builds Earful, an AI tool that aggregates product reviews into verdicts — BLCNYY · 2026-11-10
- Claude's Chrome Extension Slammed for Being Unable to Control Already-Open Tabs — Angaisb_ · 2026-11-10