←back to thread

Use Prolog to improve LLM's reasoning

(shchegrikovich.substack.com)
232 points shchegrikovich | 2 comments | 13 Oct 24 21:22 UTC | HN request time: 0.399s | source
Show context
pjmlp ◴[17 Oct 24 19:33 UTC] No.41872982[source]▶
So we are back to Japanese Fifth Generation plan from 1980's. :)
replies(5): >>41873176 #>>41873178 #>>41873253 #>>41873890 #>>41874052 #
1. linguae ◴[17 Oct 24 20:08 UTC] No.41873253[source]▶
This time around we have all sorts of parallel processing capabilities in the form of GPUs. If I recall correctly, the Fifth Generation project envisioned highly parallel machines performing symbolic AI. From a hardware standpoint, those researchers were way ahead of their time.
replies(1): >>41873372 #
2. nxobject ◴[17 Oct 24 20:22 UTC] No.41873372[source]▶
And they had a self-sustaining video game industry too... if only someone had had the wild thought of implementing perceptrons and tensor arithmetic on the same hardware!