/explore

Click through on any links that interest you or select the planets on the right to continue exploring the Outer Web.
You are here

 simonwillison.net
Qwen2.5-Coder-32B is an LLM that can code well that runs on my Mac
| | bdtechtalks.com
No-code retrieval augmented generation (RAG) with LlamaIndex and ChatGPT - TechTalks
2.9 parsecs away

Travel
| | Retrieval augmented generation (RAG) enables you to use custom documents with LLMs to improve their precision.
| | qwenlm.github.io
Qwen3-Coder: Agentic Coding in the World | Qwen
2.7 parsecs away

Travel
| | GITHUB HUGGING FACE MODELSCOPE DISCORD Today, we're announcing Qwen3-Coder, our most agentic code model to date. Qwen3-Coder is available in multiple sizes, but we're excited to introduce its most powerful variant first: Qwen3-Coder-480B-A35B-Instruct - a 480B-parameter Mixture-of-Experts model with 35B active parameters which supports the context length of 256K tokens natively and 1M tokens with extrapolation methods, offering exceptional performance in both coding and agentic tasks. Qwen3-Coder-480B-A35B-Instruct sets new state-of-the-art results among open models on Agentic Coding, Agentic Browser-Use, and Agentic Tool-Use, comparable to Claude Sonnet 4.
| | alexmuraro.me
Trying out Continue AI code assistant in VS code - Alessandro Muraro
2.4 parsecs away

Travel
| | Just found out about the Continue extension for VS Code (and JetBrains), and what's cool about it is that you can set it up with a number of AI providers, including Ollama, which runs on your local computer. In order to install Ollama first install the app on your Mac from the official website, then [...]
| | jan.schnasse.org
To vibe or not to vibe - jan.schnasse
5.2 parsecs away

Travel
| [AI summary] The page contains boilerplate privacy and cookie consent text without any actual blog post content.