684 points prettyblocks | 1 comments | 21 Jan 25 19:39 UTC | HN request time: 0.305s | source

I mean anything in the 0.5B-3B range that's available on Ollama (for example). Have you built any cool tooling that uses these models as part of your work flow?

Show context

cwmoore ◴[21 Jan 25 23:37 UTC] No.42786641[source]▶

>>42784365 (OP) #

I'm playing with the idea of identifying logical fallacies stated by live broadcasters.

replies(8): >>42787010 #>>42787653 #>>42788090 #>>42788889 #>>42791080 #>>42793882 #>>42798043 #>>42798458 #

1. vaylian ◴[22 Jan 25 10:01 UTC] No.42791080[source]▶

>>42786641 #

LLMs are notoriously unreliable with mathematics and logic. I wish you the best of luck, because this would nevertheless be an awesome tool to have.

↑

Ask HN: Is anyone doing anything cool with tiny language models?