Personal web proxies
Les Orchard is considering building his own web proxy. I had never thought about the possibilities of these technologies beyond caching before, but Les’s post has really got me thinking. I often find myself searching around for a web page I visited a few months ago and can only vaguely remember—a proxy generated searchable history (I never got the hang of using my browser’s) would be a very useful tool. In addition, the ability to cache local copies of useful documents to preserve them should the original ever go offline would be very handy. How about a proxy with an accompanying small GUI desktop application which shows your recent browsing history (the last 15 pages or so) and allows you to mark documents for bookmarking / preserving? The application and proxy server could communicate via XML-RPC.
More recent articles
- 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
- Prompt injection explained, with video, slides, and a transcript - 2nd May 2023