When George Hotz described AI-generated code as "slop," everyone knew exactly what he meant.
His blog post, "The Eternal Sloptember," names something that's been nagging at every developer who's spent real time with AI coding tools. The code appears correct. It performs correctly. And then you ship it, and something quietly breaks in a way that takes you three hours to trace.
The Thesis That Hit a Nerve
According to Hotz, AI generates "statistically plausible but subtly broken code." This encapsulates exactly how I've sensed things for a while now. The AI almost nails the solution. It almost gets the imports correct, the function signatures correct, the overall flow correct.
However, the final 10% that includes edge cases, error handling, strange interactions between your auth middleware, and that one legacy endpoint, is not as successful. Yet, that final 10% is the most important part.
