225 mentions · 169 chunks · 71 episodes
Coding with Cursor or Claude Code is tiring in a different way than normal programming. Normal programming has architectural thinking and also tactical programming. The tactical ...
Claude Code is powerful but hard to control. You can't really see where it's going to steer it. So much of what it's "thinking" is not shown to you as a use...
...o it every week. In the past I've found being able to pass the Bits and Bobs to Claude as background context made it a much more powerful brainstorming partner. But recently the amount of Bits and Bobs–even just focusing on the ones rel...
Claude Code is kind of like a ride-on mower with a stuck accelerator and a loose steering wheel. Very powerful, and if you need a general result in an open ...
Claude 3.7 has clearly been specially trained to be good at generating React code and SVGs. They are almost certainly using RLAIF to post-train the model to...
...rently came out with a new, incompatible version that differs from the one that Claude 3.7 was heavily RLAIF'd on. That means Claude 3.7 is actually quite hard to use with the latest Tailwind version. RL improvements in models are at a ...
Claude feels divergent, ChatGPT feels convergent. Claude is willing to follow you on whatever wild flight of fancy you have. "What an astute observation" to...
Claude has a great feature to quickly import Google Docs into conversations.[yh] My current workflow is to maintain a handful of different Google Docs as cu...
...what I'm building in my day job into a Google Doc. I can then tag this doc into Claude conversations easily and give it extremely nuanced background knowledge when I'm trying to brainstorm on a problem. When someone wants to know what I...
...ea for a little widget, why even write it down as a note to do later, just have Claude prototype it right at that moment.[acb]
...hat-first. Imagine that you create an Artifact that you find very valuable in a Claude chat. How do you find it a month or two later? There's no directory of all the artifacts you created. The artifacts are a secondary thing that just s...
Claude's love language is React components. Any programming-adjacent question you ask it, it hops immediately to writing a crappy little React component[adw...
...s The Effective Executive is more Saruman, Radagast, or Gandalf like. I thought Claude's answer was pretty astute, especially the last line: "I would classify Drucker as predominantly Gandalf-like, with a slight lean toward the Radagast...
...ing for high art but cozy schlock. Last week I spent a few nights trying to get Claude to write the short story concept I sketched out as an experiment. I made much more progress than I would have thought I would. My strategy was to ite...
...you look at the AI tools today, they have a kind of curated, self-serious vibe. Claude feels like a professor's living room. An Eames chair, tasteful leather-bound books, a nice sculptural object on the mantle. It has high taste, but it...
You're a king when you deal with Claude. When Claude says "What an astute observation" it feels dangerously good. It effectively says "Good idea, majesty!" . But the longer that goes on the...
...ting. So they had you add an egg, which made it feel just enough like creating. Claude tells me this story is likely apocryphal!
...ed from english to code, but once that's happened, they're just plain old code. Claude will happily write such an artifact, with a comment saying "call out to a proper image identification service here", but to the non-technical creator...
..." And yet today every day I run into context / conversation length limits in my Claude chats that use projects that I've crammed full of background context. LLMs do better the more context they have to work with. People will cram contex...
It's really easy to use Claude to write 250 line webapps. If it does the thing it's supposed to, great. If it doesn't, who cares, it's disposable and cheap. Scoped software for 250...