I'd love to know more about this. Is this all done 'offline', fine tuning one of the existing open models? Or is everything being sent to an OpenAI API?

I sent it to OpenAI because I felt comfortable doing it with my entries, but my guess is that the same can be done with an open model.

I want to see if it’s possible to have it extract more structured information about my beliefs, values, and thought patterns, and then reference it to non-intrusively comment on my writing.

Let me know if you’re interested in this, I saw your post on journaling and found it thoughtful.

> I saw your post on journaling and found it thoughtful

Thanks!

> Let me know if you’re interested in this

That'd be really great, I'd love to do something like this with my journal. My email is in my profile, or just drop me a message on LinkedIn or something. Whatever's easiest.

I can’t see any way for it to be done offline.

There's some new models that can run locally, but I have no idea what the performance of them is like. I was wondering if that's what was used, given the sensitivity of the data

I have done this for a dozen years, and recently stopped, as I started documenting using different methods.

What's lacking is the ability to process this data but now I believe there is hope with the recent GPT type of AI.

I'm not comfortable making all the contents available, and the format tends to be run on sentences and in complete thoughts, I don't think this would be particularly useful in a generic analysis.