Latest / Logosofia no Dia a Dia
The 79% AI Coder: Reasoning vs. Memorization
The latest SWE-bench results show AI coding agents hitting 79% accuracy, nearly matching human engineers. But is this real progress or just sophisticated memorization? We explore the hidden role of agent scaffolds, the shocking cost differences between models, and why harder benchmarks reveal a 40-point performance drop. Episode 1831 — myweirdprompts.com/n/1831 (permanent short link: myweirdprompts.com/703446)
The skinny
The skinny isn't ready yet — notes appear once the transcript is processed.