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

Scallop – A Language for Neurosymbolic Programming

scallop-lang.org

Post reply on HN
Print view View original

31–40 of 68 posts

Re: Scallop – A Language for Neurosymbolic Programming

#31

Post by light_hue_1 »

The problem with scallop is that no one has ever shown a single program that wasn't easier to write without it. Their papers usually contain also no examples, and the ones that do are a heck of a lot more complicated than asking the model to do it directly. The programming languages world let's them get away with this because they're excited to be relevant in the LLM universe. But I wouldn't accept any of this work if I was their reviewer; they need to write real programs and compare against baselines. Many of them. And show that their language provides any value.

Just look at the examples on their website. All 3 are lame and far easier without their language.

It's like publishing that you have a new high performance systems language and never including any benchmark. They would be rejected for that. Things just haven't caught up in the ML+PL world.

Re: Scallop – A Language for Neurosymbolic Programming

#32

Post by anonzzzies »

mark_l_watson wrote: post #28

I looked at Scallop a year ago and decided that it was not a replacement for Prolog - for me. I may re-evaluate now, thinking of smoother LLM integration as well as differentiability. Has anyone here used Scallop for a large application? I ask because in the 1980s I wrote a medium large application in Prolog and it was a nice developer experience.

Not Scallop related but did you try Mercury? It is prolog with types and flagging of deterministic functions; the Prolog we ported had a very large (... vague, I know) performance boost and that is a lot of code. Porting is gradual mostly.

Re: Scallop – A Language for Neurosymbolic Programming

#33

Post by meltyness »

The SCC example is interesting, I wonder what behavior that gens to. Reminds me of Lean, have to suspect it may make the processor quite spicy, like Lean. Also don't see clear indication that this benefits from heterogeneous compute resources.

Oh, boy, it's written in Rust!

Re: Scallop – A Language for Neurosymbolic Programming

#34

Post by mountainriver »

sigmoid10 wrote: post #11
dr_dshiv wrote: post #3

Earlier quoted context omitted.

When LLMs code in order to reason, isn’t that a combination of probabilistic reasoning and symbolic reasoning?

Neural networks are actually somewhere in between. They don't directly operate on symbolic expressions or explicit logical rules. And while they rely on probabilistic aspects for training (and sometimes for inference), they rely more on continuous-valued transformations in extremely high dimensional spaces. But if your goal is human-like intelligence, they are a pretty good bet, because we know the human brain also d…

Yes, this seems to be what the symbolists always forget. We don’t use symbolism like this, we just have very dense neural connections that emerge from scale and approximate it

Re: Scallop – A Language for Neurosymbolic Programming

#35

Post by suddenlybananas »

mountainriver wrote: post #34
sigmoid10 wrote: post #11

Earlier quoted context omitted.

Neural networks are actually somewhere in between. They don't directly operate on symbolic expressions or explicit logical rules. And while they rely on probabilistic aspects for training (and sometimes for inference), they rely more on continuous-valued transformations in extremely high dimensional spaces. But if your goal is human-like intelligence, they are a pretty good bet, because we know the human brain also d…

Yes, this seems to be what the symbolists always forget. We don’t use symbolism like this, we just have very dense neural connections that emerge from scale and approximate it

That's not really what symbolists actually argue. Read Fodor and Pylylshyn 1988 to better understand how symbolists view the relationship between symbolic representation and connectionist models. What you're saying is akin to saying there's no point in doing neuroscience or trying to understand neural-networks as its just particle physics deep down.

Re: Scallop – A Language for Neurosymbolic Programming

#37

Post by WhitneyLand »

mountainriver wrote: post #34
sigmoid10 wrote: post #11

Earlier quoted context omitted.

Neural networks are actually somewhere in between. They don't directly operate on symbolic expressions or explicit logical rules. And while they rely on probabilistic aspects for training (and sometimes for inference), they rely more on continuous-valued transformations in extremely high dimensional spaces. But if your goal is human-like intelligence, they are a pretty good bet, because we know the human brain also d…

Yes, this seems to be what the symbolists always forget. We don’t use symbolism like this, we just have very dense neural connections that emerge from scale and approximate it

So if inventing the airplane how long should one stick with a flapping bird wing design?

Re: Scallop – A Language for Neurosymbolic Programming

#38

Post by Xmd5a »

FloorEgg wrote: post #2

Ever since I learned about category theory and its relationship with symbolic reasoning I've suspected that AGI will come from elegantly combining symbolic reasoning and probabilistic reasoning. This is the first project I've seen that seems to be positioned that way. Very cool.

https://www.brunogavranovic.com/posts/2024-03-13-my-thesis-i...

Re: Scallop – A Language for Neurosymbolic Programming

#40

Post by mark_l_watson »

anonzzzies wrote: post #32
mark_l_watson wrote: post #28

I looked at Scallop a year ago and decided that it was not a replacement for Prolog - for me. I may re-evaluate now, thinking of smoother LLM integration as well as differentiability. Has anyone here used Scallop for a large application? I ask because in the 1980s I wrote a medium large application in Prolog and it was a nice developer experience.

Not Scallop related but did you try Mercury? It is prolog with types and flagging of deterministic functions; the Prolog we ported had a very large (... vague, I know) performance boost and that is a lot of code. Porting is gradual mostly.

I tried Mercury for a short while.
Post reply on HN