It’s so hard to finish an idea that is not yours and is just suggested by AI
1–10 of 74 posts
Re: It’s so hard to finish an idea that is not yours and is just suggested by AI
#2While 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.
Re: It’s so hard to finish an idea that is not yours and is just suggested by AI
#3I 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.
Re: It’s so hard to finish an idea that is not yours and is just suggested by AI
#4I 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.
[dead]
Re: It’s so hard to finish an idea that is not yours and is just suggested by AI
#5I 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/
Re: It’s so hard to finish an idea that is not yours and is just suggested by AI
#6I 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?
Re: It’s so hard to finish an idea that is not yours and is just suggested by AI
#7I 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.
Re: It’s so hard to finish an idea that is not yours and is just suggested by AI
#8While 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.
Re: It’s so hard to finish an idea that is not yours and is just suggested by AI
#9I 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 don't understand. Are you saying that AI should write notes but then they should be excluded from the AI's context?
Re: It’s so hard to finish an idea that is not yours and is just suggested by AI
#10What am I even here for if not to have my own ideas?