I have this problem even in codebases. Claude will work on something, and add detailed comments in which it extrapolates the from the design and confidently states intentions and decisions which aren't actually grounded in reality. Then, later sessions suffer when it reads back those hallucinations and treats them as canonical.
Humans can’t read minds either, but most humans aren’t so dumb as to forget what is a normative spec and what is just their own current, evolving model of the problem space. (Though some humans certainly are…)
i've been dabbling with various assistant models and instances and find that there's an interesting "idea" that pops up from their synthesis and relevancy analysis at a decent frequency. some kind of "inverse prompting" in which the machine has an angle, perspective, opportunity (based on the context it's working with/in) and the human turns those seedlings into something useful... or else decides its weed to be discarded.
While I use Claude a lot for my Omarchy plugins and Linux optimization/failure detection, I don’t use it for writing and note-taking, especially for coming up with unique ideas and driving them home by writing them through to the end.
It's so hard to finish an idea that is not yours and is just suggested by AI.
I think having AI keep it's _own_ notes in Obsidian is a good idea because it makes them convenient for you to read, but yeah you need to quarantine agent ideas from your own ideas because otherwise you get bad cito-genesis problems. https://xkcd.com/978/
I have this problem even in codebases. Claude will work on something, and add detailed comments in which it extrapolates the from the design and confidently states intentions and decisions which aren't actually grounded in reality. Then, later sessions suffer when it reads back those hallucinations and treats them as canonical.
Probably good to establish canonical spec documents up front that it can use and maintain as an independent reference?
Doesn't need to be "up front", but you do need to curate the context.
AI can't read your mind, and it will read what you (or anyone else) wrote.
Humans can’t read minds either, but most humans aren’t so dumb as to forget what is a normative spec and what is just their own current, evolving model of the problem space. (Though some humans certainly are…)
It can't but it will try and getting it to stop is often infeasible.
why would you not delete the comments? why are they saved or checked in? don't you read the code? and if you don't: ISN'T THIS WHY YOU NEED TO?
I feel like I'm losing my mind, what the fuck is wrong with all of you?
There was a related study posted awhile ago:
> When people think AI did the creative work, task meaning and effort decline
https://www.brookings.edu/articles/when-people-think-ai-did-...
i've been dabbling with various assistant models and instances and find that there's an interesting "idea" that pops up from their synthesis and relevancy analysis at a decent frequency. some kind of "inverse prompting" in which the machine has an angle, perspective, opportunity (based on the context it's working with/in) and the human turns those seedlings into something useful... or else decides its weed to be discarded.
The prompter becomes the prompted!
What am I even here for if not to have my own ideas?
“After we started thinking for you it became our society” The Matrix 1999
While I use Claude a lot for my Omarchy plugins and Linux optimization/failure detection, I don’t use it for writing and note-taking, especially for coming up with unique ideas and driving them home by writing them through to the end.
It's so hard to finish an idea that is not yours and is just suggested by AI.
It's also hard to finish an idea that is mine.
I think having AI keep it's _own_ notes in Obsidian is a good idea because it makes them convenient for you to read, but yeah you need to quarantine agent ideas from your own ideas because otherwise you get bad cito-genesis problems. https://xkcd.com/978/
This might work to keep work separate:
https://github.com/eighttrigrams/us-vs-them
I don't understand. Are you saying that AI should write notes but then they should be excluded from the AI's context?
Two different knowledge bases. One to store AI's "learned" context, the other for you to manually edit.