A chat window is built for half-formed ideas. I paste in a spec nobody else has seen and ask what's wrong with it. That's what makes it useful. It's also why the boring questions matter. Where does it go? Who can process it? What happens afterward?
1
1
11
Reviewing a week of posts side by side is richer than a command. So is looking at a header image. For that work, a page wins. I've stopped pretending this is a compromise. It's the right tool for the actual work.
1
1
8
If you run one product, your stack can be whatever makes you happy. If you run a portfolio, every tool that isn't the same across all of it adds friction with each context switch. And I context-switch a lot. scatteredonpurpose.substack.…
1
1
7
The core is tmux. One session, a window per product. When I come back the next day, every session is still running. Overnight, even. Same repos, same Claude Code sessions, no rebuild cost. If I could keep one tool, it would be this one.
1
1
1
13
My command layer is four things. tmux. Claude Code. Forgejo. A todo.md in every repo. Everything I do to move a product forward happens inside one of them. That's what I mean when I say the terminal is my command center.
1
1
11
Something unfinished, up front: last week my own tracker missed two of my posts on X. Both went out on time. I'd changed a comma in one and a word in the other, and it only counts exact matches. Almost everything I run goes through one terminal. Here's the honest tour.
1
2
2
17
I'm not a terminal purist and I'm not going to pretend to be one. Spotify is open every working hour. What's actually true is more useful. The terminal is my command center. Everything else is an attachment to that core. scatteredonpurpose.substack.…
1
1
13
Run one product, and any stack works. Run a portfolio, and every tool that isn't the same across all of it adds friction. The terminal is the one surface that stays the same, whichever product I open. scatteredonpurpose.substack.…
2
2
10
This felt like one question. It turned out to be four. What did I contribute? What rights exist in it? How do I make it distinctive? Where does the unfinished work go? Where would you draw the line: your own machine or the cloud? scatteredonpurpose.substack.…
1
1
12
A decision record I plan to keep: the first concept note, what changed after talking to readers, and the model's suggestions I rejected. It shows whether the direction came from my choices or from accepting the most convincing answer over and over. scatteredonpurpose.substack.…
1
1
12
Most AI privacy talk is about training. The controls are real. OpenAI lets individuals opt out. Anthropic has a model-improvement setting for Free, Pro, and Max. But turning training off is not the same as keeping a conversation on my own computer.
1
1
1
10
Most AI privacy talk is about training, and the controls there are real. But turning training off is not the same as keeping a conversation on my own computer. The service still has to process everything I send it. scatteredonpurpose.substack.…
1
1
11
"Just use open source" mixes up two different questions. For my purposes, the label answers nothing. I need three other answers: Where does it run? What does the app around the model send online? What does the license allow?
1
1
8
Anthropic says that if you turn its model-improvement setting off later, your data stays in training that has already started and in models already trained. So the time to decide is before I paste the spec in, not after.
1
1
10
OpenAI's Temporary Chats aren't used for training, but OpenAI may keep a copy for up to 30 days for safety. And a custom GPT that uses actions sends data to a third party under that company's privacy policy. Source: OpenAI Temporary Chat FAQ scatteredonpurpose.substack.…
1
1
12