I spent some time moving my bookmarks and workflows to Raindrop from Pocket. I'm mostly done with a short post on how and why I did that. I'd like to use the python-raindropio package to generate...
I was away from the computer for a couple of weeks. That was really nice. During my downtime and in transit, these were some of my favorite things I read in the past two weeks. I'm planning to come...
Sabrina wrote an interesting write up on solving a math problem with gpt-4o. It turned out the text-only, chain-of-thought approach was the best performing, which is not what I would have guessed.
Nostalgia: https://maggieappleton.com/teenage-desktop.
I'm looking into creating a Deno serve that can manage multiple websocket connections and emit to one after receiving a message from another. A simple way to implement this is to have a single server...
I take an irrational amount of pleasure in disabling notifications for apps that use them to send me marketing.
I enjoyed reading Yuxuan's article on whether Github Copilot increased their productivity. I personally don't love Copilot but enjoy using other AI-assisted software tools like Cursor, which allow...
I read this post by Steph today and loved it. I want to try writing this concisely. I imagine it takes significant effort but the result are beautiful, satisfying and valuable. It's a privilege to...
Having gotten more into using llama 7b and 30b lately, this take seems likes it could hold water. Model inference still isn't free when you scale a consumer app. Maybe I can use llama3 for all my...
I read Jason, Ivan and Charles' blog post on Modal about fine tuning an embedding model. It's a bit in the weeds of ML for me but I learn a bit more every time I read something new.