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

Learn Prolog Now (2006)

lpn.swi-prolog.org

Post reply on HN
Print view View original

81–90 of 251 posts

Re: Learn Prolog Now (2006)

#81

Post by riku_iki »

jodrellblank wrote: post #54
disambiguation wrote: post #40

I am once again shilling the idea that someone should find a way to glue Prolog and LLMs together for better reasoning agents. https://news.ycombinator.com/context?id=43948657 Thesis: 1. LLMs are bad at counting the number of r's in strawberry. 2. LLMs are good at writing code that counts letters in a string. 3. LLMs are bad at solving reasoning problems. 4. Prolog is good at solving reasoning problems. 5. ??? 6. LLM…

> "4. Prolog is good at solving reasoning problems." Plain Prolog's way of solving reasoning problems is effectively: for person in [martha, brian, sarah, tyrone]: if timmy.parent == person: print "solved!" You hard code some options, write a logical condition with placeholders, and Prolog brute-forces every option in every placeholder. It doesn't do reasoning . Arguably it lets a human express reasoning problems bet…

Even in your example (which is obviously not correct representation of prolog), that code will work X orders magnitude faster and with 100% reliability compared to much more inferior LLM reasoning capabilities.

Re: Learn Prolog Now (2006)

#82

Post by fifilura »

Declarative languages are fantastic to reason about code.

But the true power is unlocked once the underlying libraries are implemented in a way that surpassesthe performance that a human can achieve.

Since implementation details are hidden, caches and parallelism can be added without the programmer noticing anything else than a performance increase.

This is why SQL has received a boost the last decade with massively parallel implementations such as BigQuery, Trino and to some extent DuckDB. And what about adding a CUDA backend?

But all this comes at a cost and needs to be planned so it is only used when needed.

Re: Learn Prolog Now (2006)

#83

Post by exasperaited »

vidarh wrote: post #18
mattbettinson wrote: post #4

In university, Learning prolog was my first encounter with the idea that my IQ may not be as high as I thought

I also found it mindbending. But some parts, like e.g. the cut operator is something I've copied several times over for various things. A couple of prototype parser generators for example - allowing backtracking, but using a cut to indicate when backtracking is an error can be quite helpful.

"Keep your exclamation points under control. You are allowed no more than two or three per 100,000 words of prose."

Elmore Leonard, on writing. But he might as well have been talking about the cut operator.

At uni I had assignments where we were simply not allowed to use it.

Re: Learn Prolog Now (2006)

#84

Post by lkuty »

Avicebron wrote: post #64
disambiguation wrote: post #40

I am once again shilling the idea that someone should find a way to glue Prolog and LLMs together for better reasoning agents. https://news.ycombinator.com/context?id=43948657 Thesis: 1. LLMs are bad at counting the number of r's in strawberry. 2. LLMs are good at writing code that counts letters in a string. 3. LLMs are bad at solving reasoning problems. 4. Prolog is good at solving reasoning problems. 5. ??? 6. LLM…

@goblinqueen, you around?

@YeGoblynQueenne Dunno if it will ping the person

Re: Learn Prolog Now (2006)

#85

Post by troupo »

nuc1e0n wrote: post #62
jodrellblank wrote: post #54

Earlier quoted context omitted.

> "4. Prolog is good at solving reasoning problems." Plain Prolog's way of solving reasoning problems is effectively: for person in [martha, brian, sarah, tyrone]: if timmy.parent == person: print "solved!" You hard code some options, write a logical condition with placeholders, and Prolog brute-forces every option in every placeholder. It doesn't do reasoning . Arguably it lets a human express reasoning problems bet…

What makes you think your brain isn't also brute forcing potential solutions subconciously and only surfacing the useful results?

human brains are insanely powerful pattern matching and shortcut-taking machines. There's very little brute forcing going on.

Re: Learn Prolog Now (2006)

#86

Post by szundi »

riku_iki wrote: post #81
jodrellblank wrote: post #54

Earlier quoted context omitted.

> "4. Prolog is good at solving reasoning problems." Plain Prolog's way of solving reasoning problems is effectively: for person in [martha, brian, sarah, tyrone]: if timmy.parent == person: print "solved!" You hard code some options, write a logical condition with placeholders, and Prolog brute-forces every option in every placeholder. It doesn't do reasoning . Arguably it lets a human express reasoning problems bet…

Even in your example (which is obviously not correct representation of prolog), that code will work X orders magnitude faster and with 100% reliability compared to much more inferior LLM reasoning capabilities.

This is not the point though

Re: Learn Prolog Now (2006)

#87

Post by jnpnj »

disambiguation wrote: post #40

I am once again shilling the idea that someone should find a way to glue Prolog and LLMs together for better reasoning agents. https://news.ycombinator.com/context?id=43948657 Thesis: 1. LLMs are bad at counting the number of r's in strawberry. 2. LLMs are good at writing code that counts letters in a string. 3. LLMs are bad at solving reasoning problems. 4. Prolog is good at solving reasoning problems. 5. ??? 6. LLM…

Can't find the links right now, but there were some papers on llm generating prolog facts and queries to ground the reasoning part. Somebody else might have them around.

Re: Learn Prolog Now (2006)

#88

Post by mindcrime »

disambiguation wrote: post #40

I am once again shilling the idea that someone should find a way to glue Prolog and LLMs together for better reasoning agents. https://news.ycombinator.com/context?id=43948657 Thesis: 1. LLMs are bad at counting the number of r's in strawberry. 2. LLMs are good at writing code that counts letters in a string. 3. LLMs are bad at solving reasoning problems. 4. Prolog is good at solving reasoning problems. 5. ??? 6. LLM…

I am once again shilling the idea that someone should find a way to glue Prolog and LLMs together for better reasoning agents.

There are definitely people researching ideas here. For my own part, I've been doing a lot of work with Jason[1], a very Prolog like logic language / agent environment with an eye towards how to integrate that with LLMs (and "other").

Nothing specific / exciting to share yet, but just thought I'd point out that there are people out there who see potential value in this sort of thing and are investigating it.

[1]: https://github.com/jason-lang/jason

Re: Learn Prolog Now (2006)

#89

Post by Gormisdomai »

mindcrime wrote: post #88
disambiguation wrote: post #40

I am once again shilling the idea that someone should find a way to glue Prolog and LLMs together for better reasoning agents. https://news.ycombinator.com/context?id=43948657 Thesis: 1. LLMs are bad at counting the number of r's in strawberry. 2. LLMs are good at writing code that counts letters in a string. 3. LLMs are bad at solving reasoning problems. 4. Prolog is good at solving reasoning problems. 5. ??? 6. LLM…

I am once again shilling the idea that someone should find a way to glue Prolog and LLMs together for better reasoning agents. There are definitely people researching ideas here. For my own part, I've been doing a lot of work with Jason[1], a very Prolog like logic language / agent environment with an eye towards how to integrate that with LLMs (and "other"). Nothing specific / exciting to share yet, but just thought…

Related: LLMs trained on "A is B" fail to learn "B is A"

https://arxiv.org/abs/2309.12288

Re: Learn Prolog Now (2006)

#90

Post by baq »

bobbylarrybobby wrote: post #78
disambiguation wrote: post #40

I am once again shilling the idea that someone should find a way to glue Prolog and LLMs together for better reasoning agents. https://news.ycombinator.com/context?id=43948657 Thesis: 1. LLMs are bad at counting the number of r's in strawberry. 2. LLMs are good at writing code that counts letters in a string. 3. LLMs are bad at solving reasoning problems. 4. Prolog is good at solving reasoning problems. 5. ??? 6. LLM…

IIRC IBM’s Watson (the one that played Jeopardy) used primitive NLP (imagine!) to form a tree of factual relations and then passed this tree to construct Prolog queries that would produce an answer to a question. One could imagine that by swapping out the NLP part with an LLM, the model would have 1. a more thorough factual basis against which to write Prolog queries and 2. a better understanding of the queries it sh…

Please tell me that's approximately what Palantir Ontology is, because if it isn't, I've no idea what it could be.
Post reply on HN