Quoting Florian Herrengt

Simon Willison's Blog News
ai software-engineering debugging code-complexity opinion

Summary

A quoted excerpt from Florian Herrengt's blog post discusses how AI-assisted development can lead to undebuggable, convoluted codebases where even AI tools like Claude can't fix issues, highlighting a growing problem in software engineering.

No content available
Original Article
View Cached Full Text

Cached at: 08/12/26, 04:19 PM

# A quote from Florian Herrengt Source: [https://simonwillison.net/2026/Aug/12/florian-herrengt/](https://simonwillison.net/2026/Aug/12/florian-herrengt/) 12th August 2026 > But then users start to report a weird bug\. It's the 4th time your team has been trying to fix it\. I mean\.\.\. asking AI to fix it\. Unfortunately, it seems like not even Fable can figure it out\. You go talk to the person who worked on this feature\. "So where does the data come from?" "Hmm\.\.\. actually I don't know\. Let me ask Claude\." You sit next to each other watching an endless wall of text appear on the screen\. Neither of you has any idea whether any of it is true but Claude seems very confident\. \[\.\.\.\] This project has become so convoluted, with so many layers and services, that no one on your team could possibly start to understand what's going on\. —[Florian Herrengt](https://blog.florianherrengt.com/ai-removing-middle-class-software-engineering.html),AI is removing the middle class of software engineering

Similar Articles

Quoting Florian Herrengt

Simon Willison's Blog

A quote from Florian Herrengt about how AI-generated code can lead to convoluted projects where no one understands the system, highlighting risks in software engineering.

Working With AI: A concrete example

Hacker News Top

The author shares a concrete example of using Claude AI to debug a parsing regression in hyperscript, highlighting the strengths and weaknesses of AI-assisted development and cautioning against over-reliance.

On AI Coding and Its Discontents

Lobsters Hottest

Cal Newport reflects on the initial enthusiasm for AI coding tools like Claude Code and the growing disillusionment among developers due to hidden bugs, quality issues, and unsustainable workflows, arguing that outsourcing all code production to AI is not currently viable.

@garrytan: https://x.com/garrytan/status/2054064931515855118

X AI KOLs Following

Garry Tan argues that AI coding agents like Claude Code and Codex have changed software engineering by making high test coverage affordable, creating a 'complexity ratchet' that ensures code quality improves over time without sacrificing speed.

@SaitoWu: https://x.com/SaitoWu/status/2053101671035851216

X AI KOLs Timeline

The article summarizes a talk by Matt Pocock criticizing 'specs-to-code' approaches, arguing that solid software engineering fundamentals like TDD and modular design are more critical than ever for effectively using AI coding assistants like Claude Code.