Rendered at 16:51:28 GMT+0000 (Coordinated Universal Time) with Cloudflare Workers.
synalx 39 minutes ago [-]
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.
mrtesthah 20 minutes ago [-]
Probably good to establish canonical spec documents up front that it can use and maintain as an independent reference?
lupire 18 minutes ago [-]
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.
pydry 5 minutes ago [-]
It can't but it will try and getting it to stop is often infeasible.
throwaway613746 10 minutes ago [-]
[dead]
dan_gggggg 39 minutes ago [-]
[dead]
chessucation 5 minutes ago [-]
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.
helsinkiandrew 8 minutes ago [-]
There was a related study posted awhile ago:
> When people think AI did the creative work, task meaning and effort decline
What am I even here for if not to have my own ideas?
zazuke 1 hours ago [-]
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.
lupire 17 minutes ago [-]
It's also hard to finish an idea that is mine.
empath75 31 minutes ago [-]
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/
lupire 15 minutes ago [-]
I don't understand. Are you saying that AI should write notes but then they should be excluded from the AI's context?
swiftcoder 2 minutes ago [-]
Two different knowledge bases. One to store AI's "learned" context, the other for you to manually edit.
AI can't read your mind, and it will read what you (or anyone else) wrote.
> When people think AI did the creative work, task meaning and effort decline
https://www.brookings.edu/articles/when-people-think-ai-did-...
It's so hard to finish an idea that is not yours and is just suggested by AI.