(shchegrikovich.substack.com)

379 points shchegrikovich | 1 comments | 13 Oct 24 21:22 UTC | HN request time: 0.359s | source

Show context

YeGoblynQueenne ◴[17 Oct 24 21:53 UTC] No.41874200[source]▶

That's not going to work. Garbage in - Garbage out is success-set equivalent to Garbage in - Prolog out.

Garbage is garbage and failure to reason is failure to reason no matter the language. If your LLM can't translate your problem to a Prolog program that solves your problem- Prolog can't solve your problem.

replies(3): >>41874322 #>>41875551 #>>41876345 #

mountainriver ◴[18 Oct 24 01:27 UTC] No.41875551[source]▶

>>41874200 #

Agree, reasoning has to come from within the model. These are hacks that only work in specific use cases

replies(1): >>41878173 #

1. YeGoblynQueenne ◴[18 Oct 24 10:53 UTC] No.41878173[source]▶

>>41875551 #

Yep. Specifically ones for which there are lost of examples of Prolog programs on the web so an LLM can learn the correct translation more easily.

↑

Use Prolog to improve LLM's reasoning