Day 4: Lillian
Mark Pilgrim’s set of case studies is beginning to shape together. I’ve been following responses to it through his “Further reading on today’s posts” referral tracking tool—reception has been overwhelmingly positive, with almost universal praise for Mark’s decision to use the case study format to drive home his point. kcalder criticised Mark’s suggestion that colour blind users wouldn’t get much out of
images on the web, and Mark has apologised and altered the case study accordingly. SubAverage called Mark “preachy” and posted a parody (mentioned in passing by Dave Winer). All this and we’re only on day 4.
More recent articles
- 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
- Delimiters won't save you from prompt injection - 11th May 2023
- Weeknotes: sqlite-utils 3.31, download-esm, Python in a sandbox - 10th May 2023
- Leaked Google document: "We Have No Moat, And Neither Does OpenAI" - 4th May 2023
- Midjourney 5.1 - 4th May 2023