Claude bros know how to measure performance. They just don’t.
https://www.youtube.com/watch?v=xeU208KqeRc&list=UU9rJrMVgcXTfa8xuMnbhAEA - video
https://pivottoai.libsyn.com/20260113-if-ai-coding-is-so-good-where-are-the-performance-numbers - podcast
time: 7 min 34 sec
In b4 METR drops the next shoddy study and the promptfondlers go wild
the most robust study in AI coding! cos they built it from toothpicks instead of toilet paper