AIDan Luu argues AI coding agents frequently make errors that would get a human developer firedThe essay critiques LLM benchmarks for failing to capture real-world workflow friction.4 Sources, 92d ago, first seen 92d agoCombined views3.3K4 Sources, first seen 92d ago33 likesCombined views3.3K4 Sources, first seen 92d ago33 likes
