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

CauseNet: Towards a causality graph extracted from the web

causenet.org

Post reply on HN
Print view View original

71–80 of 131 posts

Re: CauseNet: Towards a causality graph extracted from the web

#71

Post by johnecheck »

bbor wrote: post #5

> CauseNet aims at creating a causal knowledge base that comprises all human causal knowledge and to separate it from mere causal beliefs Pretty bold to use a picture of philosophers as your splash page and then make a casual claim like this. To say the least, this is an impossible task! The tech looks cool and I'm excited to see how I might be able to work it into my stuff and/or contribute. But I'd encourage the au…

Indeed. I can't take an epistemology project seriously if it has no humility.

Building a perfectly accurate model of the world isn't possible. We need to create tools that make it easier for regular people to build more accurate models, not delude ourselves with dreams of perfection.

Re: CauseNet: Towards a causality graph extracted from the web

#72

Post by jijijijij »

eru wrote: post #55
lemonwaterlime wrote: post #50

Earlier quoted context omitted.

My take is that the GP was implicitly referring to Gödel’s Incompleteness Theorems with the implication being that a system that reasons completely about all the human topics and itself is not possible. Therefore, you’d need multiple such systems (plural) working in concert.

That doesn't make much sense. If you take multiple systems and make them work in concert, you just get a bigger system.

> If you take multiple systems and make them work in concert, you just get a bigger system.

The conclusion may be wrong, but a "bigger system" can be larger than the sum of its constituents. So a system can have functions, give rise to complexity, neither of its subsystems feature. An example would be the thinking brain, which is made out of neurons/cells incapable of thought, which are made out of molecules incapable of reproduction, which are made from atoms incapable of catalyzing certain chemical reactions and so on.

Re: CauseNet: Towards a causality graph extracted from the web

#73

Post by energy123 »

jiggawatts wrote: post #22
tgv wrote: post #14

This makes little sense to me. Ontologies and all that have been tried and have always been found to be too brittle. Take the examples from the front page (which I expect to be among the best in their set): human_activity => climate_change. Those are such a broad concepts that it's practically useless. Or disease => death. There's no nuance at all. There isn't even a definition of what "disease" is, let alone a way t…

Even more importantly, it's not even a simple probability of death, or a fraction of a cause, or any simple one-dimensional aspect. Even if you can simplify things down to an "arrow", the label isn't a scalar number. At a bare minimum, it's a vector, just like embeddings in LLMs are! Even more importantly, the endpoints of each such causative arrow are also complex, fuzzy things, and are best represented as vectors.…

You're losing interpretability and scrutability, but gaining detail and expressiveness. You have no way to estimate the vectors in a causal framework, all known methods are correlational. You have no clean way to map the vectors to human concepts. Vectors are themselves extremely compressed representations, there is no clear threshold beyond which a representation becomes "proper".

Re: CauseNet: Towards a causality graph extracted from the web

#74

Post by tossandthrow »

jijijijij wrote: post #68
lemonwaterlime wrote: post #50

Earlier quoted context omitted.

My take is that the GP was implicitly referring to Gödel’s Incompleteness Theorems with the implication being that a system that reasons completely about all the human topics and itself is not possible. Therefore, you’d need multiple such systems (plural) working in concert.

I believe, neither the expansion of Gödel's theorems to "everything", non-formalized systems, nor the conclusion of a resolution by harnessing multiple systems in concert, are sound reasoning. I think, it's a fallacious reductionism.

What is a non-formalized system?

I am very curious on this. In particular, if you are able to split systems into formalized and non formalized, then I thinks there are quite some praise and a central spot in all future history books for you!

Re: CauseNet: Towards a causality graph extracted from the web

#75

Post by jijijijij »

qsi wrote: post #67
dr_dshiv wrote: post #34

Earlier quoted context omitted.

Democritus (b 460BCE) said, “I would rather discover one cause than gain the kingdom of Persia,” which suggests that finding true causes is rather difficult.

Felix, qui potuit rerum cognoscere causas. [0] Virgil. [0] https://en.m.wikipedia.org/wiki/Felix,_qui_potuit_rerum_cogn...

Virgili, hoc postremo dico: mihi nomen non est Felix.

Re: CauseNet: Towards a causality graph extracted from the web

#76

Post by CuriouslyC »

tgv wrote: post #14

This makes little sense to me. Ontologies and all that have been tried and have always been found to be too brittle. Take the examples from the front page (which I expect to be among the best in their set): human_activity => climate_change. Those are such a broad concepts that it's practically useless. Or disease => death. There's no nuance at all. There isn't even a definition of what "disease" is, let alone a way t…

It's pretty easy to outline a high level ontology and let LLMs annotate/link it into something pretty useful, you can even have a benchmark suite using that ontology via LLM as a judge to progressively optimize it.

Re: CauseNet: Towards a causality graph extracted from the web

#77

Post by mark_l_watson »

This might be of at least some value to augment training LLMs? I spent a lot of time in the 1980s and early 1990s using symbolic AI techniques: conceptual dependency, NLP, expert systems, etc. While two large and well funded expert system projects I worked on (paid for by DARPA and PacBell) worked well, mostly symbolic AI was brittle and required what seemed like an i finite amount of human labor.

LLMs are such a huge improvement that the only real use I see in projects like Cause et, the defunct OpenCyc project, etc. the only possible practical use might be as a little extra training data.

Re: CauseNet: Towards a causality graph extracted from the web

#78

Post by CuriouslyC »

eru wrote: post #55
lemonwaterlime wrote: post #50

Earlier quoted context omitted.

My take is that the GP was implicitly referring to Gödel’s Incompleteness Theorems with the implication being that a system that reasons completely about all the human topics and itself is not possible. Therefore, you’d need multiple such systems (plural) working in concert.

That doesn't make much sense. If you take multiple systems and make them work in concert, you just get a bigger system.

Sort of, the guardrail here IMO is you have an ontology processor that basically routes to a submodule, and if there isn't a submodule present it errors out. It is one large system, but it's bounded by an understanding of its own knowledge.

Re: CauseNet: Towards a causality graph extracted from the web

#79

Post by energy123 »

bckr wrote: post #61
Nevermark wrote: post #38

Earlier quoted context omitted.

That was very well said. One quibble, and really mean only one: > a high-dimensional probabilistic causal framework Deep learning models aka neural network type models, are not probabilistic frameworks. While we can measure on the outside a probability of correct answers across the whole training set, or any data set, there is no probabilistic model. Like a Pachinko game, you can measure statistics about it, but the…

What’s the relationship between what you’re saying and the concepts of “temperature” and “stochasticity”? The model won’t give me the same answer every time.

The probability distribution that the model outputs is deterministic. The decoding method that uses that distribution to decide what next token to emit may or may not be deterministic. If we decide to define the decoding method as part of "the model", then I guess the model is probabilistic.

It's also worth noting that the parameters (weights and biases) of the model are random variables, technically speaking, and this can be considered probabilistic in nature. The parameter estimates themselves are not random variables, to state the obvious. The estimates are simply numbers.

Re: CauseNet: Towards a causality graph extracted from the web

#80

Post by ProofHouse »

johnecheck wrote: post #71
bbor wrote: post #5

> CauseNet aims at creating a causal knowledge base that comprises all human causal knowledge and to separate it from mere causal beliefs Pretty bold to use a picture of philosophers as your splash page and then make a casual claim like this. To say the least, this is an impossible task! The tech looks cool and I'm excited to see how I might be able to work it into my stuff and/or contribute. But I'd encourage the au…

Indeed. I can't take an epistemology project seriously if it has no humility. Building a perfectly accurate model of the world isn't possible. We need to create tools that make it easier for regular people to build more accurate models, not delude ourselves with dreams of perfection.

Well of course because no such model of the world can or does exist
Post reply on HN