Armin Ronacher ran a GPT-6 Astra 'software factory' for 35 hours, burned ~4B tokens, and got nothing useful
Astra for Coding: Why Are We Doing This Again?
Flask creator Armin Ronacher let GPT-6 Astra run a fully autonomous 'software factory' to add virtual threads and lexical scoping to CPython. After 35 hours and roughly 4 billion tokens, it delivered zero value. Astra excessively uses Python string splicing to edit C files instead of patch tools, producing low-quality code. Ronacher suspects the training over-rewards long-horizon task completion but under-penalizes bad code. He acknowledges Astra is impressive at 3D generation and reverse engineering, but for now he doesn't know how to use it for real software engineering.
Why it matters: A concrete 35-hour, 4-billion-token failure from a well-known engineer, plus his read on why models still don't fit real engineering work.