Xanadu was waiting for agents • Hacker News Board

Re: Xanadu was waiting for agents

#61

Post by yencabulator » Fri, Sep 04, 2026, 5:02 PM UTC

BobbyTables2 wrote: post #39

Don’t Lamport timestamps require all nodes to be known in advance? Powerful concept but impractical and far too unscalable to be used globally.

You can manage version vectors with large random IDs: [(random_id, clock), ...]. That's not the problem. The problem is you can never remove a node from the clock (without losing properties).

Most of the Xanadu data structure implementations, like ZigZag, just don't perform well enough at web scale.

Re: Xanadu was waiting for agents

#62

Post by patcon » Fri, Sep 04, 2026, 6:00 PM UTC

more-coffee wrote: post #55

patcon wrote: post #33

Earlier quoted context omitted.

Ah, so like the distance between ambition and impact in metaphor/synthesis? I like that.

Do you mean that LLMs are unable to use metaphors effectively? (Just clarifying because English is not my first language)

heh, yeah, just "unable to use metaphor effectively" is what I meant :)

i guess I'm saying it in a funny way because my brain has always thought about semantic space (and the act/object of conversation itself) in a very spatial way, and it seems that LLMs have a similar tendency

to elaborate: "unable to use metaphor effectively" seems to have multiple dimensions of failure, in which I find the distance metaphor to make easier to explore. A mind-like thing can (1) not know how to make the leaps (and so never try to make them), or (2) it can leap too ambititously and land in faraway places that don't have any deep symmetry in meaning... it can (3) also maybe "not stick the landing" while jumping someplace that theoretically might have merit (in a sense of global vs local scale, maybe being ok at the global scale orienting, but not local scale)...

So in my defence, I think there are failure modes of "being ineffective at metaphor" that are masked by speaking in plainer language :)

Re: Xanadu was waiting for agents

#63

Post by siramikvarze » Fri, Sep 04, 2026, 9:06 PM UTC

yencabulator wrote: post #60

bobajeff wrote: post #5

Reading this makes me wish someone would really try to make Project Xanadu a reality. A network built on Content Addressable Storage and a Version Control System is some thing I'd really like to see invested in.

The spec was kept proprietary and patented until about 2019. All you had before that was ramblings by an eccentric character who was 100% sure he was correct. https://sentido-labs.com/en/library/201904240732/Xanadu%20Hy... Now that we can actually read it, it's pretty much Urbit levels of kookiness all over. There's implementations. They're not very useful to a layperson. http://www.open.xanadu.com/

> Bottom crums in the granfilade represent atoms. Atoms come in two varieties: characters and orgls. Character bottom crums are stored as spans of characters, rather than individual bytes. These consist of a pointer to a block of physical storage, either in core or on disk, containing the bytes themselves, and an (integer) length, telling the number of bytes in the block. Since each of these bytes has an implicit wid of 0.0.0.0.1, the character span has a wid of 0.0.0.0.〈number of characters in the span〉. Orgl bottom crums are stored in a similar fashion, but instead of literal data bytes, pointers to the fulcrums of orgls (poomfilades) are stored.

Was this jargon normal in 1984 because we hadn't invented words like "addresses" and "structs" yet?