←back to thread

Learn Prolog Now

(lpn.swi-prolog.org)
237 points rramadass | 2 comments | | HN request time: 0.399s | source
Show context
disambiguation ◴[] No.45902807[source]
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. LLMs are good at writing prolog that solves reasoning problems.

Common replies:

1. The bitter lesson.

2. There are better solvers, ex. Z3.

3. Someone smart must have already tried and ruled it out.

Successful experiments:

1. https://quantumprolog.sgml.net/llm-demo/part1.html

replies(16): >>45903080 #>>45903178 #>>45903192 #>>45903204 #>>45903228 #>>45903263 #>>45903361 #>>45903376 #>>45903458 #>>45903841 #>>45904155 #>>45904166 #>>45904490 #>>45906435 #>>45907115 #>>45908306 #
1. mindcrime ◴[] No.45904166[source]
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

replies(1): >>45904239 #
2. Gormisdomai ◴[] No.45904239[source]
Related: LLMs trained on "A is B" fail to learn "B is A"

https://arxiv.org/abs/2309.12288