Link · 13m · dev.to ↗
Archive — page 2
Articles

Link · 7m · engineering.atspotify.com ↗
Portal by Spotify cut my Claude Code token usage by 90%

Link · 4m · arxiv.org ↗
HANDBOOK.md: A Benchmark for Long-Context Agentic Instruction Following

Link · 12m · laude.org ↗
Headlong: a microharness for persistent agents

Link · 17m · discoveredmaterials.com ↗
Material Discovery Bench
Link · 49m · danluu.com ↗
How does programming language affect token efficiency and correctness?
The ReAct agent loop fits on a page; production does not
Testing AI agents: evals are the unit tests of agent systems
Postmortems for something nobody typed

Link · 51m · huggingface.co ↗