← Front page

Machine Learning Street Talk · Sunday, June 28, 2026

AI Agent-Based Code Generation and Verification Concerns

Thomas Ahle compares Anthropic's success in reproducing a C compiler with 40,000 agents to his own projects. He expresses concern that agentic coding can lead to complex, unmanageable codebases ('spaghetti monsters') that even their creators may not fully understand, posing a challenge for long-term maintenance and verification.

personThomas AhlecompanyAnthropic

The tape

3 quotes
So the idea is we get a shitload of agents and we reproduce the function of this software based on these tests and we do it recursively and generically and so on.
Thomas Ahle
Now, my contention with this is I think that it's not about where you end up, it's not about the functions and the tests passing. It's about how you got there and how structured it is.
Thomas Ahle
So there is this tendency with agentic coding to build a spaghetti monster which seems to work, but because if you think about it in this project, you're talking about I think you said there's like 500 or more 500,000 lines of code and in five years time, there's all of this code that probably, you know, you folks haven't read most of it.
Thomas Ahle
Heard on Machine Learning Street Talk — “The Thermodynamic AI Computing Chip - Thomas Ahle, published Sunday, June 28, 2026. Heardvine summarizes and quotes with attribution and timestamps, and links to the original everywhere.
Transcribed via Gemini audio transcription · $0.06