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
13
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
11
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
8
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
10
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
11
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
9
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
10
"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
7
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
9
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
11
A local model can't make an idea original or create rights in it. It only changes who receives my unfinished work. It turned out to be four questions: what did I contribute, what rights exist, how do I make it distinctive, where does unfinished work go? scatteredonpurpose.substack.…
2
2
11
A chat window is built for half-formed ideas. I describe a feature before I know if it belongs. I paste in a spec nobody else has seen. That's why the boring questions matter: where does that material go, who can process it, what happens after? Part 4 of a four-part series.
1
2
2
11
Two shortcuts I don't trust. Asking a second model doesn't certify originality. It just widens the search. And asking a model to confirm its own suggestion has never existed isn't a test at all.
1
1
9
The model knows a lot about readers in general. It doesn't know mine.
1
1
8
In a 2024 study, short stories written with access to AI ideas were rated as more novel and more useful. They also came out more alike. So I want to ask two questions about any suggestion. Is this better? And is this more like everything else? scatteredonpurpose.substack.…
1
1
11
Ask a model for ten variations, and you often get one idea in ten outfits. New names. New colors. And the user still does exactly the same thing. What I want instead: alternatives that actually work differently.
1
1
13
These are habits I want to build in. The first: write a concept note before opening the chat. Who is it for? What do they struggle with? What do I think should change? What am I unsure about? Which answers did I see, and which am I assuming? It needs to exist, not be right.
1
1
2
14
When I type "help me design a book app" into a chat, I've handed over almost every decision before it starts. Audience, problem, features, feel. The model will do that well. That's the risk. I end up polishing a direction I never chose. Part 3 of a four-part series.
1
1
2
14
Before I open a chat with a model, I want a short note written first. Who is this for? What do they struggle with? Which answers did I actually see, and which am I assuming? It gives me a fixed point to measure every suggestion against. scatteredonpurpose.substack.…
1
1
20
None of this stops someone else from landing in the same place on their own. I could never prevent that. What the habits give me is better reasons. A model offers more possibilities than I can produce alone. I still need a reason to choose. scatteredonpurpose.substack.…
1
2
14