Qwen3-Coder: Agentic coding in the world(qwenlm.github.io)

680 points by danielhanchen 1 year ago | 300 comments

Qwen Team blog post announcing Qwen3-Coder, their most agentic code model to date, with links to GitHub, Hugging Face, ModelScope and Discord.

Analyzing the codebase of Caffeine, a high performance caching library(adriacabeza.github.io)

246 points by synthc 1 year ago | 44 comments

A review of OpenAI o1 and how we evaluate coding agents(cognition.ai)

24 points by thomasahle 2 years ago | 2 comments

The unbearable slowness of AI coding(joshuavaldez.com)

91 points by aymandfire 1 year ago | 59 comments

AGENTS.md outperforms skills in our agent evals(vercel.com)

472 points by maximedupre 9 months ago | 182 comments

Vercel blog post reporting that an AGENTS.md file outperformed skills for teaching coding agents Next.js 16 APIs in their agent evals.

Agentic Engineering(addyosmani.com)

16 points by fagnerbrack 5 months ago | 1 comments