Xanadu was waiting for agents | Hacker News Reader

Xanadu was waiting for agents

zed.dev

156 pointsnsm62 comments

This post buys into the common narrative about Xanadu, that it was a fundamentally good idea that failed due to some combination of poor execution, being too far ahead of its time, and the market not caring about quality (with this post in particular focusing mostly on the second thing).

In my view, Gwern makes a compelling counterargument: Xanadu was a fundamentally bad idea. The parts of it that weren't incorporated into the World Wide Web either solved problems no one actually had, or couldn't have constituted a stable equilibrium between users and publishers (i.e., even if it'd been magically willed into existence, it'd have quickly fallen apart). https://gwern.net/xanadu

Great post, as a fan of Gwern and Nelson I wonder how I missed it (and how I didn’t get an invite to the party :’)

The “too genius, too early” is a common trope in the tech industry, but it rarely stands scrutiny. When you inspect the claim up close you almost inevitably find out a variation of that “bad design/solves a problem no one really has/does not create the virtuous cycles needed for success”.

But as an inventor it might be easier for one’s ego to tell yourself “i was just ahead of my time” than “my judgement was completely off”.

If you’re an inventor of any kind, the “try lots of small things, see which ones seem to stick, narrow down on those” approach seems preferable to “commit your entire identity to one big thing”, but there is a certain siren song to the latter.

> But as an inventor it might be easier for one’s ego to tell yourself “i was just ahead of my time” than “my judgement was completely off”.

This has more to do with the economy than ego. When one's ability to eat and have shelter relies on "inventing" the inventor will invent a new wheel to sell to a tribe that's pre-wheel.

This no longer works as well in software given the number of people who code, and the various forms of automation (AI or design tool that emits code, etc) to assist those who do not.

No pulling the wool with a fancy abstraction alone. It's just math relative to a matrix of desirable values loaded in memory.

The normal progression of technology coupled to economic models written down by long dead who were too busy enslaving people to invent indoor plumbing.

I went down a rabbit hole circa 2015 sketching out a system which was going to solve the language + world model problem which of course only needed to be partially implemented to solve a specific family of problems. In a broad sense think Palantir but with 20x the TAM because it is also an application builder.

I studied Xanadu a lot for this analysis because the system would need huge amounts of annotated text so it was requirement that "any" document could be marked up with commentary or structured markup turning the "explainable" idea bidirectionally so that humans could explain to the system what and why it is and the system could "talk back" in the same "language". Practically "any" reduced to HTML + PDF.

Transclusion was important to the vision because if, say, constants in a source code file came out of a standards document the link between the two ought to be preserved.

I can't say the internals would have looked like Xanadu at all and there wouldn't have been those micropayments.

This economic equilibrium reality kills so many cool-sounding ideas. Someone has to actually run them, and if it's more soul-sucking than soul-giving (for some definition of "soul" which may include money) it won't happen. It's not always money, sometimes it's just really hard to keep the service up or to block spam.

I agree with Gwern. And also Nelson kind of lost my respect after he spend the rest of his life bashing and complaining on how bad the WWW is compared to his ideas.

Ted is super specific and inflexible about lots of technical details that just don't work. I don't want to air out dirty laundry here but it's non-existence in any robust state wasn't for lack of trying.

Also it's a feature, not a bug. If we were all pragmatists ...

This was my feeling trying to grok why I want or need Delta.

Interesting. This and the other posts I've seen about Delta seems to exist in that liminal space, were it's difficult to tell if the author has had a brilliant insight, that they struggle to convey to anyone who's not yet had the same insight; or if they've simply gone slightly mad.

It's a similar sense I get with reading Nelson (after being able to think about his ideas for a while, I'm quite certain it was mostly genius and only a little bit of lunacy).

It remains to see how Delta will turn out.

On a side-note; my initial reaction to the headline was; no. Xanadu wasn't missing agents.

I do think I see where the author is going, though; and I think I agree that agents might be a new tool that might facilitate some hypertext ideas. Not Xanadu perhaps. But some other, more pragmatic and less magic place - but a place that is a little more magical than where we are now.

And it intersects a bit with an experiment we started at work; migrating our modest web site from WordPress to a static site combining 11ty (https://11ty.dev) (we already lean heavily on typescript for our application development) and visual studio code with frontmatter cms (https://frontmatter.codes) - and AI/LLMs.

AI helps with making a static page version of our site, and adopting to 11ty.

The idea is that with trivial push-to-deploy setup, our business people, with the help of AI in vs code, will be able to work directly with 11ty and git to make changes, do reviews and publish changes.

A hill that would probably have been too steep for them to climb just six months ago.

So in reference to the theme of realizing a better hypertext system with the help of AI, we're sort of doing the same thing, it turns out: mix solid, boring tools (static site gen, typescript, editor, version control, CI, static hosting) and some AI - to hopefully allow more users leverage both tooling and AI in an empowering way.

We've just stated the experiment - we may yet fly too close to the sun, and end up falling back to a traditional CMS.

I think not are the same the only thing that differentiates them is adoption. If people show interest in the thing you are a genius if they don't you are mad/crazy.

The madman and the genius are similar in that they disagree with the world at large/prevailing wisdom. Where they differ is that the madman loses the fight while the genius (eventually) wins.

One reason I have some hope for this approach is that we start by removing complexity by going to a static web site first.

We remove WordPress, database, configuration, templates - a lot of cruft.

Then we can add it back as needed for keeping edits and publishing simple. It might turn out we hardly need anything from 11ty, thanks to AI making editing more automatic.

I think (the collective) we, are (mostly by accident) building systems that are at least one dimension or level of higher abstraction than before AI.

Unfortunately with AI, higher abstraction doesn't automatically mean less complexity, or better managed complexity.

I think 95% of systems being built now with Al and on top of - or including Al - will turn out to be highly complected mountains of madness.

Complexity in itself is not an interesting measure but it's a proxy for an interesting measure: time and cost to build/maintain.

A more complicated program that is built and maintained with LLM assistance is cheaper and faster to build and fix than even a less complicated program built without. It's even the same without LLMs: once React achieved critical density and "won" the JS framework wars, building React apps became cheaper and faster even than building plain HTML/JS apps.

calling what someone else finds interesting “not an interesting measure” is itself something that calls for an interested measure.

I strongly disagree. Incidental complexity is the enemy good emergent properties of a system; security, auditability, stability, testability, maintainability...

Well it unironically takes a thousand years to integrate the ideas revealed in a single acid trip. Doesn't mean we shouldn't try!

This sounds like one agent at each junction point, that may or may not be running the same model and architecture as the previous one, and they need to constantly crawl each other or just a protocol to call each other. But then you have a million of then constructing a docuverse web all having an agent who all need to know each other and its all connections and each a database repository.

Well you only need links that exist, and those that are created.

In a paragraph it may exist in one node that is referenced and that node may be a collection of other nodes, or each sentence or even each word points to other nodes, how much does each model know and what does it keep in its database. A point to the next node is not necessarily durable or versioned, and that goes for each node is connects to.

A single paragraph could have thousands or more sources, references, and each source would need versioning and depending on version it may well point to different nodes in prior or future versions.

A proper version of a paragraph would then need to know this, or expect that all nodes with an agent will be durable and rational and interoperable but if you build on that premise it will not work in the real world.

All unless you keep the docuverse limited in scope to a few data stores and agents who comprehend that spatial universe, and it is a form of an intranet

One of my favorite LLM-smells to train myself to sniff out is how well the author can tie two seemingly disparate ideas together into something compelling or novel. The more ambitious the synthesis and the less impressed I am the more likely I am to assume it was at least partially the work of an LLM.

Previously, "Jimi Hendrix Was a Systems Engineer" <https://spectrum.ieee.org/jimi-hendrix-systems-engineer>

The content was clearly AI written. It made no sense. Even crazy humans such as Terry Davis made more sense than such AI slop generated "blog" entries.

That this is published by the lead of a pretty popular piece of software is disconcerting. The UI for the IDE itself and the web design for Delta even have that Claude Code "Claudhaus" look to them.

I'm beginning to think that this sort of behavior is actually an inverted counter-signal. The average person attuned to LLM's markings may find these things distasteful. But certain individuals or organizations may feel right at ease seeing them.

And funding them.

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

I like that.

Exactly.

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 :)

> Xanadu had a final failure mode, this one self-inflicted

Skimmed the article, saw this, and then my AI fatigue closed the tab.

A system that never forgets is not always a good thing. I'm not sure what the maximal scope (beyond editors) the author wishes this applied to is, but there are many cases where it is a positive for things to be erased. Privacy concerns is one example.

Ummet Ozcan - Xanadu: https://www.youtube.com/watch?v=9uMtnH7cABg

I don't think he's waiting for agents.

How awful. And AI-generated. There must be a disclaimer - too many websites steal time now via agents.

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.

It's not a reality for a lack of trying. Multiple people have spent (literal!) lifetimes working on Xanadu and multiple businesses poured a great deal of money and effort into it way back in the day.

It continues to not be a thing because, even though the idea is superficially appealing to a certain engineer mind and that's why people get sucked into the cult, in reality it's not something anybody wants and it's solving a problem nobody has.

Right. I knew those people back when Autodesk owned Xanadu. The fundamental problem was that tracking and paying for text ownership and viewing down to the word level isn't really very useful. The Xanadu people were libertarians into micropayments. Everything is pay per view in Xanadu. Not cheap views, expensive ones, like Lexis/Nexis.

Also, they had no idea how to deal with either images or distributed systems.

> Also, they had no idea how to deal with either images or distributed systems.

What would make images harder than anything else? My naive self thinks, "hey, isn't that just one long base64-encoded word?" Apparently not, or they would've done it and moved on.

And why do you say that about distributed systems? What I've read of Xanadu (primarily the Wired article) made it sound like there'd be a relatively small number of commercial servers everyone else would subscribe to. Cue IBM's "five computers are enough" apocrypha. Is that what you mean?

I find everything about Xanadu fascinating, in kind of a slow-moving train crash sort of way, and would love hearing more bystander takes!

> What would make images harder than anything else?

Because diffs of image files are not very useful. Nelson's thing was very fine-grained tracking of who wrote what. That doesn't map well to images or video.

Ah, got it. That makes sense from what I casually know about the project.

I just finished writing a long rant on the other Project Xanadu related submission today where I specifically noted that Xanadu has a feature called a "permascroll" where everything you publish gets written into the permascroll and then transcluded into actual documents. This is a very "video editor" concept. Actually, the Xanadu model of transclusions and history would translate extremely well into nonlinear video editing; it's arguably better for video than it is for text.

Images wouldn't work unless you made a "Xanalogical image editor" that stores a list of edits and references to source images as you made or imported them. The tumbler number structure would have to be extended to include rectangular references into image files. It would work in theory, but in practice would probably bog down every computer that needed to load an image, and you'd get hit with shittons of fees for each one.

I can only imagine audio having to be stored as some kind of standardized DAW project file, with transcluded sample packs that would get you micro-transactioned for each one.

Man, this was a really silly idea...

Huh, that 2nd to last article almost sounds like Amiga mod files. You pieced together samples, often, um, “borrowed” from other mods, into song-specific selection, then included a list of which samples to trigger at which frequency at which time. For example, you’d include one bass drum and one snare drum, and instructions on how to arrange them into rhythms.

Xanadu as a DAW might look a lot like that, except with explicit and documented reuse of another person’s samples.

A complex system cannot be "made" to work. It either works or it does not. A simple system, designed from scratch, sometimes works. Some complex systems actually work. A complex system that works is invariably found to have evolved from a simple system that works. A complex system designed from scratch never works and cannot be patched up to make it work. One has to start over, beginning with a working simple system. https://en.wikipedia.org/wiki/Systemantics

You’ll hear/read many people opining that it actually wasn’t a good idea.

I counter that it’s a great idea for many things. The problem is that something good enough and far cheaper is already all over the Earth: the web.

Just like Hurd and Minix might have technical merit that’d make them “better” than Linux, Linux is good enough and already here.

Check out IPLD (the model that powers IPFS), which translates hash-linked DAGs and handles merkle DAGs (git) natively. There's been several attempts to build Xanadu'ish things on various types of networks, web2, web3, p2p, etc, but it just doesn't seem to be what the majority wants. Maybe someday...

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?

Tell me you use an LLM to write everything without telling me...

A clock for a world with no center.

Names that can't lie.

Convergence without coordination.

Storage too cheap to delete.

Machines summoned in milliseconds.

OK, got it.

I wish someone here could introduce me to Ted Nelson, I would have loved to interview him! And yes, I've been building the "Xanadu" vision since 2011:

https://github.com/Qbix <-- hosting and editing your own websites

https://github.com/Intercoin <-- blockchain since 2018

https://github.com/Safebots <-- AI agents since 2026

https://github.com/Safebots/Safecloud <-- for example, micropayments

I'm not so sure the article is written with AI. I'd love to hear from the author on that.

If not, someone is a native in LLMese. Conveys little about what it actually is, or connected to how Delta works and is mostly talking about some abstract metaphoric relation. I remember some article on how LLMs throw in identifiers without much understanding of the indetified, other than its similiarity to another thing in text (methaphoric speech).

Have you read Nelson?

Interview him while you still can. I encourage you to seek out whoever Ted's contact people are and try to get that interview in. Make it long and thorough, and put it on YouTube and archive it.

http://www.thetednelson.com/contact.php

My Claude session must have been busy writing this as this article was being written.

Warning: this repo likely contains everything that you should not do.

https://gitworkshop.dev/npub17g32uxml7y4rf4jwlju6fd58nhzaafd...

Nelson was a pioneer of computing? No, he is a pioneer of computing.

Well let's not forget Zigzag. This is hyperstructure and Ted's greatest achievement. If you want to try it out, Gzz 0706.jar runs on Java https://www.nongnu.org/gzz/download.html

> So when web technology exploded in the '90s, developers bypassed xanalogical computing in favor of ease: links are simple strings which break if their target moves. Maintenance became users' problems — instead of the system's responsibility — but it was easy for anyone to ship fast, and they did.

developers bypassed - Really not a fan of phrases like these from a CEO.

Usually developers have to work within an organisational hierarchy that doesn't grant them infinite time or money.

>Flat was good enough.

Then agents arrived.

So, with just that we went from 1990s early internet to AI agents.

That's a time jump so jarring that it makes heavily-modified '81 DeLorean owners jealous.

Don’t Lamport timestamps require all nodes to be known in advance?

Powerful concept but impractical and far too unscalable to be used globally.

Like IP addresses, right.

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.

>Ted Nelson has been on my mind a lot this year.

For anyone else that's been thinking a lot about Ted this year, I recommend this (weird) youtube series:

https://www.youtube.com/watch?v=pGpBQgZ5IsI&list=PLsfH1Ahi4S...

Agents were already an idea on the 2000's, even if not AI powered, e.g. Agent TCL.

https://ieeexplore.ieee.org/document/612217

Xanadu sounds like it would work well with git and absolutely abysmal with LLMs.

Doesn’t structured data work best with symbolic not statistical AI?

Why would anyone want to put out accurate structured data in the AI era where unpoisoned data is worth a hard drive's weight in gold? Structured data will all be like: we open on <date day="Monday">Friday</date>

I'm always a fan of Zed blogs but this one I hope is just for attracting investors

I regret to say that this is well polished slop, but ultimately slop at the end of the day.

It seems that the user wanted to say something like "DeltaDB is a DAG" and then replaced the DAG part with some obscure graph-based project that the LLM had suggested, but otherwise has no connection to agentic development.

...so what is it?

https://delta.dev/

Does it splice the agents thinking process into the commits or what?

Maybe it needs a demo video or something.

Reply on news.ycombinator.com