Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

The semantic web is now widely adopted

csvbase.com

Post reply on HN
Print view View original

231–240 of 269 posts

Re: The semantic web is now widely adopted

#231

Post by wslh »

tossandthrow wrote: post #153
ubertaco wrote: post #150

Well, the immediate initial test failed for me: I thought, "why not apply this on one of my own sites, where I have a sort of journal of poetry I've written?"...and there's no category for "Poem", and the request to add Poem as a type [1] is at least 9 years old, links to an even older issue in an unreadable issue tracker without any resolution (and seemingly without much effort to resolve it), and then dies off with…

Having worked in this field for a bit, this uncovers an even more fundamental flaw: The idea that we can have a single static ontology.

Mostly, the problems of a semantic web are covered in the history of Cyc[1].

When I started to use LLMs I thought that was the missing link to convert content to semantic representations, even taking into account the errors/hallucinations within them.

[1] https://en.wikipedia.org/wiki/Cyc

Re: The semantic web is now widely adopted

#232

Post by amarant »

pessimizer wrote: post #166
amarant wrote: post #113

Earlier quoted context omitted.

That's even more interesting! The only non-religious meaning of soul I've ever heard is a music genre, but then English is my second language. I tried googling it and found this meaning I wasn't aware of: emotional or intellectual energy or intensity, especially as revealed in a work of art or an artistic performance. "their interpretation lacked soul" Is this the definition used? I'm not sure how a JSON document is…

It's early 20th century (and later) black American dialect to say things "have soul" or "don't have soul." In the West, Black Americans are associated with a mystical connection to the Earth, deeper understandings, and suffering. So LLMs are not gritty and down and dirty, and don't get down. They're not the real stuff.

Mystical connection? Now you're back to religion.

If you wanna be down you gotta keep it real, and mysticism is categorically not that.

Re: The semantic web is now widely adopted

#233

Post by weego »

'it makes social sharing look a bit nicer' being the only benefit that can scraped from the barrel as a benefit undermines the entire premise.

It's not widely adopted, it's used as an attempted growth hack in a few locations that may or may not be of use (with value being relative to how US centric your and your audiences Internet use is)

Re: The semantic web is now widely adopted

#234

Post by pablomendes »

That statement is both kind of true and, well, revisionist. Originally there was a strong focus on logics, clean comprehensive modeling of the world through large complicated ontologies, and the adoption of super impractical representation languages, etc. It wasn't until rebellious sub-communities went rogue and pushed for pragmatic simplifications that things got any widespread impact at all. So here's to the crazy ones, I guess.

Re: The semantic web is now widely adopted

#235

Post by glenstein »

openrisk wrote: post #64

The semantic web standards are sorely lacking (for decades now) a killer application. Not in a theoretical universe of decentralized philosopher-computer-scientists but in the dumbed down, swipe-the-next-30sec-video, adtech oligopolized digital landscape of walled gardens. Providing better search metadata is hardly that killer app. Not in 2024. The lack of adoption has, imho, two components. 1. bad luck: the Web got…

I am not sure I understand the fixation on a "killer app" in the context of web standards. We are talking about things like, say, XML, or SVG or HTTP/2. They can have their rationale and their value simply by serving to enable organic growth of a web ecosystem. I think I agree most with your last sentence and should define success more in those terms, aspiring to a better web.

Re: The semantic web is now widely adopted

#236

Post by EGreg »

openrisk wrote: post #64

The semantic web standards are sorely lacking (for decades now) a killer application. Not in a theoretical universe of decentralized philosopher-computer-scientists but in the dumbed down, swipe-the-next-30sec-video, adtech oligopolized digital landscape of walled gardens. Providing better search metadata is hardly that killer app. Not in 2024. The lack of adoption has, imho, two components. 1. bad luck: the Web got…

Why do we need web standards for the semantic web anymore when we have LLMs?

Just make LLMs more ubiquitous and train them on the Web. Rather than crawling or something. The LLMs are a lot more resilient.

Re: The semantic web is now widely adopted

#237

Post by Pet_Ant »

lo_zamoyski wrote: post #225
dboreham wrote: post #201

Earlier quoted context omitted.

I take the other side of this trade, and have since c. 1980. I say that semantics is a delusion our brains creates. Doesn't really exist. Or conversely is not the magical thing we think it is.

How are you oblivious of the performative contradiction that is that statement? Please tell me you're not an eliminativist. There is nothing respectable about eliminativism. Self-refuting, and Procrustean in its methodology, denying observation it cannot explain or reconcile. Eliminativism is what you get when a materialist refuses or is unable to revise his worldview despite the crushing weight of contradiction and…

TIL:

https://en.wikipedia.org/wiki/Eliminative_materialism

> Eliminative materialism (also called eliminativism) is a materialist position in the philosophy of mind. It is the idea that the majority of mental states in folk psychology do not exist. Some supporters of eliminativism argue that no coherent neural basis will be found for many everyday psychological concepts such as belief or desire, since they are poorly defined. The argument is that psychological concepts of behavior and experience should be judged by how well they reduce to the biological level. Other versions entail the nonexistence of conscious mental states such as pain and visual perceptions.

Re: The semantic web is now widely adopted

#238

Post by Spivak »

safety1st wrote: post #34
trainyperson wrote: post #30

Are there any tools that employ LLMs to fill out the Semantic Web data? I can see that being a high-impact use case: people don’t generally like manually filling out all the fields in a schema (it is indeed “a bother”), but an LLM could fill it out for you – and then you could tweak for correctness / editorializing. Voila, bother reduced! This would also address the two reasons why the author thinks AI is not suited…

Bringing an LLM into the picture is just silly. There's zero need. The author (and much of HN?) seems to be unaware that it's not just thousands of websites using JSON-LD, it's millions. For example: install WordPress, install an SEO plugin like Yoast, and boom you're done. Basic JSON-LD will be generated expressing semantic information about all your blog posts, videos etc. It only takes a few lines of code to exten…

I guess where do you go from basic info that can be machine generated, to rich information that's worth consuming for things other than link previews and specific Google Search integrations?

Re: The semantic web is now widely adopted

#239

Post by naasking »

lo_zamoyski wrote: post #225
dboreham wrote: post #201

Earlier quoted context omitted.

I take the other side of this trade, and have since c. 1980. I say that semantics is a delusion our brains creates. Doesn't really exist. Or conversely is not the magical thing we think it is.

How are you oblivious of the performative contradiction that is that statement? Please tell me you're not an eliminativist. There is nothing respectable about eliminativism. Self-refuting, and Procrustean in its methodology, denying observation it cannot explain or reconcile. Eliminativism is what you get when a materialist refuses or is unable to revise his worldview despite the crushing weight of contradiction and…

> Eliminativism is what you get when a materialist refuses or is unable to revise his worldview despite the crushing weight of contradiction and incoherence.

Funny, because eliminativism to me is the inevitable conclusion that follows from the requirement of logical consistency + the crushing weight of objective evidence when pitted against my personal perceptions.

Post reply on HN