GeoPlanet data available again (via) Good news: the Yahoo! GeoPlanet data dump is available again. An issue with one of their data providers meant they had to remove that supplier’s data from the dump, but it’s now been separated and the dataset is live gain. By the end of 2010 they intend to derive all of the data from completely open sources.
- 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