/explore
|
You are here 
|
ivanmisic.net | ||
| | | | |
www.anup.io
Claude Code skills work best when you treat them as workstations, not prompts: folders with scripts, gotchas, templates, and progressive disclosure that manage the agent's attention budget at runtime. |
|
| | | | | ||
| | | | |
willschenk.com
I've been writing a lot over at The Focus AI about how I'm actually using AI day-to-day, and three recent pieces have kind of converged into a single idea that I want to pull together here. The short version: I don't really build "apps" anymore. I build habitats for agents. The three pieces Claude Code, not Code was about how Claude Code isn't really a coding tool - it's a workflow orchestrator. I use it to manage hiring pipelines, track my health data, draft newsletters, automate grocery shopping. The key insight was: don't just ask Claude to do things, ask it to document how it did them so it can do them again. |
|
| | | | | ||
| | | | |
passo.uno
At the end of The writing was always the cheap part, I alluded to the fact that tech writers need to pick up new habits and skills, but didn't dig into what that entails. These days, any LLM can put together plausible docs with some context and a simple prompt. So what is it that a tech writer should be learning now? Despite the fact that the AI landscape is ever shifting under our feet, I should be able to give you some actionable directions. Buckle up. |
|
| | | | | ||
| | | | |
www.engadget.com
Amazon is investing up to $4 billion in OpenAI rival Anthropic as a way to provide deep learning and other services to its Amazon Web Service (AWS) customers. |
|
| | | |||
