Every Mac since macOS 13 (allegedly) ships a pair of daemons whose only purpose in life is to build a graph about who you are, whom you know, how those people are related to you and to each other, how you communicate with them, where you go, what you do and when. In this post, we look into how this system works and give you a tool to peek into your own graph.
Is it? I know there’s ai in the domain, but I don’t get that vibe from the style, and I just checked out the claimed authors and am confident they’re real people who’ve been writing since before LLMs could do it well.
The AI accent has progressed and Claudespeak is essentially this. There’s no blatant tells but my brain has been fried from seeing too much ai content that I can detect it now. This is a surprisingly deslopped version but it still feels pretty ai generated to me (not to mention the website design).
Yup, your LLMdar is better than mine, as the other reply to me links to the author admitting it on HN. I’d like to be better at detecting it, but if the price is having to read loads of mediocre prose then the price is too damn high.
No, it is definitely there and real, I deleted the databases and blocked them from being rebuilt on my mac yesterday. People can use LLMs to do useful work, especially if they already know what they are doing.
Delete ~/Library/IntelligencePlatform (or back it up to a different directory if you’re worried about things breaking and want to be able to put it back) then make an empty file in place of the directory with touch ~/Library/IntelligencePlatform
Good advice. Also for passer-bys if you get hit with the Operation not permitted bullshit, just make sure the app you’re using has Full Disk Access since this is considered a “protected folder”.
Automated messaging systems that send us important or relevant information have been around for quite a while now. Ignoring a message simply because of the way it was created is rarely wise.
seriously. I can deal with an inrot overly techy writer, but if you use the lying machine to mediate your communication, I can’t trust anything you say.
Is it? I know there’s ai in the domain, but I don’t get that vibe from the style, and I just checked out the claimed authors and am confident they’re real people who’ve been writing since before LLMs could do it well.
The AI accent has progressed and Claudespeak is essentially this. There’s no blatant tells but my brain has been fried from seeing too much ai content that I can detect it now. This is a surprisingly deslopped version but it still feels pretty ai generated to me (not to mention the website design).
Yup, your LLMdar is better than mine, as the other reply to me links to the author admitting it on HN. I’d like to be better at detecting it, but if the price is having to read loads of mediocre prose then the price is too damn high.
https://news.ycombinator.com/item?id=50403613
The author says it’s mostly AI. “In my defense, only the technical parts are AI. But, thanks for the feedback; I thought I had unsloped it enough…”
Also at Git, in the readme for the tool to explore the data, “iKnow is fully LLM-generated and may not be 100% accurate.”
so this whole story is bullshit?
No, it is definitely there and real, I deleted the databases and blocked them from being rebuilt on my mac yesterday. People can use LLMs to do useful work, especially if they already know what they are doing.
How does one do this?
Delete
~/Library/IntelligencePlatform(or back it up to a different directory if you’re worried about things breaking and want to be able to put it back) then make an empty file in place of the directory withtouch ~/Library/IntelligencePlatformGood advice. Also for passer-bys if you get hit with the
Operation not permittedbullshit, just make sure the app you’re using has Full Disk Access since this is considered a “protected folder”.Maybe so, but if someone can’t be bothered to write it, I can’t be bothered to read it.
Automated messaging systems that send us important or relevant information have been around for quite a while now. Ignoring a message simply because of the way it was created is rarely wise.
seriously. I can deal with an inrot overly techy writer, but if you use the lying machine to mediate your communication, I can’t trust anything you say.