
mufeez
@moofeez • 1,763 subscribers
exploring ML systems and agents infra @linear, fmr @meta. @uwaterloo SE alum
Videos

I post-trained Qwen3-Coder to fix bugs using an actual debugger. The result: Solve rate: 70% → 89% Median turns to fix: 46 → 19 (-59%) Instead of just reading code or print-debugging, it: - reasons from execution - inspects live variables and call stacks - sets breakpoints, steps, and evaluates expressions
mufeez123,560 görüntüleme • 1 ay önce
Daha fazla içerik yok.