Forum Posts Feed
AI-infused
< Next Topic | Back to topic list | Previous Topic >
Pages: ‹ First < 7 8 9 10 11 12 13 >
Posted by satis
Oct 5, 2025 at 06:26 PM
Dr Andus wrote:
satis wrote:
>
>>
>>Dr Andus wrote:
>>
>>>every time I tried to sign up and have read through their privacy
>>>policy during sign-up, it seemed to me that they were asking me to
>>allow
>>>them complete and absolute access to all my data and everything that
>>I’m
>>>doing
>>
>>I don’t think that’s accurate.
>
>I
>I was referring to the various
>agreements during the signing-up process specifically, which gave me
>this impression.
I think you got a misimpression. The documentation and links show pretty clearly that ‘complete and absolute access to all my data and everything that I’m doing’ does not comport with all the clear documentation about user privacy and user control and ownership of their data.
Posted by Dr Andus
Oct 19, 2025 at 11:26 AM
I’m very late to the AI party, in fact I’m still just looking in through the window, wondering whether to go in…
But I did find the latest AI extension for RoamResearch intriguing, especially the feature (3. Ask Your Graph Agent) where you can ask the agent to query and summarise your notes in the Roam graph:
https://roam-research.kit.com/posts/commentarii-roamani-roam-live-ai
I haven’t used Roam as a knowledge base (I’m mainly using it for organising my daily todos and as a journal of what I’ve got done), but with this extension I can suddenly see the appeal of Roam as a Zettelkasten.
While even this extension can offer many different uses of AI, my main interest is to be able to query my knowledge bases (such as my reading notes, my own research notes, and my personal diary entries), to gain insights which otherwise would be difficult or very time-consuming to get or ones that I might not even think of.
I gather that NotebookLM offers this capability, plus I’ve seen other options where you can create a library for an AI solution to query locally (such as the HP AI Companion) or point an AI agent some other way to query a local folder on one’s hard drive.
So I’m shopping around for a solution where I could accomplish the above, in a way where I could control what level of privacy I’m willing to give up for each query (e.g. HP AI Companion does give you the option to keep the query on the machine, or to use a cloud AI).
For instance I wouldn’t want to share my personal journal entries with an online AI (though I could query them with a local small language model on my laptop), but I’m less precious of my reading notes.
Interestingly, the above Roam extension does allow for specifying different privacy levels, but it’s hard to know what that means and in any case Roam data is already in the cloud.
Anyway, I’m wondering what your experience has been with this sort of “querying your own notes” use of AI agents, if anyone here has some experience with all this to share.
Posted by satis
Oct 19, 2025 at 03:52 PM
I’ve experimented with querying my own notes using Perplexity Pro, and recently started using Perplexity’s Comet web browser. (Full local file integration is not yet publicly available in Comet, only in dev builds.)
You can point Perplexity to a local folder and have it analyze the contents, but this requires using the Model Context Protocol filesystem access feature in the Perplexity Mac App, with specific setup requirements.
https://www.perplexity.ai/help-center/en/articles/11502712-local-and-remote-mcps-for-perplexity
https://www.perplexity.ai/comet/gettingstarted
https://apps.apple.com/us/app/perplexity-ask-anything/id6714467650
I’ve used it to look at folders of text files and PDFs to extract insights and summaries and overviews. You can say things like “Summarize this document” or “Explain the findings on pages 10 to 15”. For some arcane PDFs I can get clear and simple explanations of complex topics, and can translate materials and explore related topics on the web. I’ve had it proofread documents and I’ve experimentally used it to get feedback, brainstorm ideas, and refine/rewrite my writing - though it usually rips all personality out of the rewrites.
(ChatGPT is often a lot better for rewriting suggestions, though it too churns out bland academic text.)
Perplexity lets you select up to 10 files at once (up to 40MB each) to perform cross-document queries and comparisons. It analyzes short files entirely, while “longer” files are processed to extract “the most relevant parts for your specific query,” meaning it sometimes loses context or misses meaning in larger documents.
I just copy-pasted the above into Comet/Perplexity and asked it to rewrite for clarity, and it instantly gave me this mild rewrite (with its usual tic of inserting a ‘—’ throughout its text):
I’ve been testing Perplexity Pro’s ability to query my personal notes, and I recently started using their Comet web browser. Note that Comet’s full local file integration is currently limited to developer builds—it’s not yet available to the public.
The Perplexity Mac app can analyze local folders through the Model Context Protocol (MCP) filesystem access feature, though this requires specific setup steps detailed in their documentation.
I’ve used it to analyze folders containing text files and PDFs, extracting insights, summaries, and overviews. You can ask questions like “Summarize this document” or “Explain the findings on pages 10 to 15.” This has been particularly useful for dense PDFs—I can get clear explanations of complex topics, translate materials, and explore related information on the web. I’ve also used it for proofreading and experimentally for feedback and brainstorming, though the rewrites typically strip out all personality. (ChatGPT generally handles rewrites better, though it also produces bland, academic-sounding text.)
Perplexity supports batch processing of up to 10 files simultaneously, with each file capped at 40MB. This enables cross-document queries and comparisons. While it analyzes short files in their entirety, longer documents are processed selectively to extract “the most relevant parts for your specific query”—which means it can sometimes lose context or miss meaning in larger files.
Posted by Dr Andus
Oct 19, 2025 at 11:12 PM
satis wrote:
>Perplexity lets you select up to 10 files at once (up to 40MB each) to
>perform cross-document queries and comparisons. It analyzes short files
>entirely, while “longer” files are processed to extract “the most
>relevant parts for your specific query,” meaning it sometimes loses
>context or misses meaning in larger documents.
Thanks for sharing your experience.
I came across an article today which talked about the need to combine hundreds of Obsidian files into a single file, so that NotebookLM can read them:
https://www.xda-developers.com/move-obsidian-knowledge-vault-to-notebooklm-with-plugins/
Your mention that Perplexity also limits you to 10 files.
It makes me wonder if it’s better to combine thousands of files into a single file when I’m importing them into Obsidian then, if I wanted to use AI at one point to analyse them.
For instance I have probably around 5000 individual diary entries in ConnectedText, and I was planning to import them into Obsidian, but now I’m wondering if it’s better to combine them into a single text file.
Well, as I’m typing this here, I’m thinking ‘why am I bothering my fellow forum members with this question, when I could probably ask this directly in one of the AI “answer engines”’...
We’re getting to a situation where one could be just spending the entire day posting one query and prompt after another, as one is going through their day…
Posted by Andy Brice
Oct 20, 2025 at 12:44 PM
Just this morning I searched “Capri” on Google. The AI overview told me it is a fictional island. But it’s very much a factual island.