Here's an interesting new embedding/RAG technique, described by Anthropic but it should work for any embedding model against any other LLM. One of the big challenges in implementing semantic search …

I’ve written a lot about how I’ve been using Claude to build one-shot HTML+JavaScript applications via Claude Artifacts. I recently started using a similar pattern to create one-shot Python utilities,...

A genome browser in your Jupyter notebook

Neat new RAG technique (with a snappy name) from John Berryman: > The big idea of Roaming RAG is to craft a simple LLM application so that the LLM assistant …

Extraordinary demo by Vaibhav Srivastav. Here's Hugging Face's [SmolLM2-1.7B-Instruct](https://huggingface.co/HuggingFaceTB/SmolLM2-1.7B-Instruct) running directly in a web browser (using WebGPU, so requires Chrome [for the moment](https://github.com/gpuweb/gpuweb/wiki/Implementation-Status)) demonstrating structured text extraction, converting a text …

Run like this: uv run https://gist.githubusercontent.com/simonw/848a3b91169a789bc084a459aa7ecf83/raw/44fe7e0b326832e88beb83748b50104e5e7f70d0/follow_theirs.py - follow_theirs.py

This PEP specifies a metadata format that can be embedded in single-file Python scripts to assist launchers, IDEs and other external tools which may need to interact with such scripts.

Hi, in this quick demo, I showcase using Apple shortcuts for legal timekeeping. I demonstrate triggering Siri, creating time entries, and automating tasks. No specific action requested, just an explor...

@Ed__Johns: This is a single uncut video, showing a robot learning several tasks instantly, after just one demonstration each ... This is possible because we've now been able to achieve in-context lea...

Setting up my new MacBook Pro from scratch

@Tim_Dettmers: This is the most important paper in a long time . It shows with strong evidence we are reaching the limits of quantization. The paper says this: the more tokens you train on, the more.....

YouTube video by The Eric Ries Show