#llm evaluation

2 stories

#software engineering #startups #technology #action space #ai coding #ai models #benchmarks #code quality #coding agents #component analysis #context management #harness design

How to build better coding agents
Researchers break down the components that make AI coding agents work, revealing what actually matters for performance.
arXiv · 1m
Coding is solved, but the slop isn't
An Earendil researcher tried to measure how sloppy AI-written code really is, and found agents produce twice the mess humans do.
Earendil · 2m · 6 views