302 mentions · 217 chunks · 92 episodes
...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...
Claude can do impressive synthesis and summarization tasks. I fed it as much of the Bits and Bobs as I could, and then asked it a specific strategic questio...
...code in an age of LLMs. He can build extremely impressive applications. He asks Claude or another LLM to write the "goop" – the black boxed, magical incantations he needs to wire into his application to get it to do something. It used t...
...ystem to a very different, highly centralized outcome. A month or so ago we got Claude Sonnet 3.5, and now we have an open weights model in the same ballpark. The open system has caught up! If you had to bet on a single model family tod...
Imagine a product that is effectively Claude style Artifacts, but with an open and private ecosystem. The open and private properties are a bonus, a deal sweetener when picking between two items...
...topped reading code, you just copy and paste back and forth between VS Code and Claude and add the text "fix the bug" you're not learning nearly as much any more. This kind of fear is not new; it historically has been brought up for eve...
A friend who self-describes as "not very technical" used Claude to make his own Discord Bot. How empowering! A trick he used: after having it write the original code, say "make it better" and Claude figured out a ...
Unpacking subtexts takes patience and savviness. Claude is patient and pretty savvy! Claude is great at doing straussian reads of writing to unpack hidden subtexts.
...ts. If you can get something to work in last-gen models (e.g. GPT 3.5 Turbo, or Claude Haiku) then it will definitely work / work better in newer models. But if you do it the reverse, you might find that it's only viable in the expensiv...
... it into a successfully bootstrapped aggregator play to get staying power. With Claude Opus outcompeting GPT4 in some areas, it looks like this will be a costly and hard-fought race. There's an orthogonal bet, though. You can bet that t...