Vibe coding and agentic engineering are getting closer than I'd like
Simon Willison · Simon Willison · 2026-05-06
(No summary yet for this item — extraction summaries are still backfilling.)
Appears in
Extraction
Topics: vibe-codingagentic-engineeringai-coding-toolssoftware-engineering-practiceai-trust
Claims
- The distinction between vibe coding and professional agentic engineering is blurring as AI coding agents become more reliable.
- Increased AI coding reliability is causing professional engineers to reduce code review, creating 'normalization of deviance' risks.
- The entire software development lifecycle was designed around humans producing a few hundred lines of code per day, and that assumption is now broken.
- AI-generated projects can be superficially indistinguishable from carefully crafted ones, making software quality evaluation much harder.
- AI coding tools amplify existing engineering expertise rather than replace it, preserving the value of experienced engineers.
Key quotes
Weirdly though, those things have started to blur for me already, which is quite upsetting.
There's an element of the normalization of deviance here - every time a model turns out to have written the right code without me monitoring it closely there's a risk that I'll trust it at the wrong moment in the future and get burned.
The entire software development lifecycle was, it turns out, designed around the idea that it takes a day to produce a few hundred lines of code. And now it doesn't.