Facets. New open source visualization and data exploration tool from Google (“Disclaimer: This is not an official Google product”, whatever that means). It’s intended for visualizing machine learning datasets but it’s obviously useful outside of ML as well—any time you need to understand a large dataset this looks like it could be extremely useful. Ships with example jupyter notebooks and an easy mechanism for embedding the Facets interactive UI directly inside a notebook cell.
- Understanding GPT tokenizers - 8th June 2023
- Weeknotes: Parquet in Datasette Lite, various talks, more LLM hacking - 4th June 2023
- It's infuriatingly hard to understand how closed models train on their input - 4th June 2023
- ChatGPT should include inline tips - 30th May 2023
- Lawyer cites fake cases invented by ChatGPT, judge is not amused - 27th May 2023
- llm, ttok and strip-tags - CLI tools for working with ChatGPT and other LLMs - 18th May 2023