News for hackers. Stuff that matters.

A comment on Show HN: I built a tiny LLM to demystify how language models work.

Re:Show HN: I built a tiny LLM to demystify how language mod... by amelius on Monday April 06, 2026 @07:18AM (#47659428)
> A 9M model can't conditionally follow instructions

How many parameters would you need for that?

[ Parent | on HN ]
Re:Show HN: I built a tiny LLM to demystify how language mod... by armanified on Monday April 06, 2026 @07:50AM (#47659698)
My initial idea was to train a navigation decision model with 25M parameters for a Raspberry Pi, which, in testing, was getting about 60% of tool calls correct. IMO, it seems like around 20M parameters would be a good size for following some narrow & basic language instructions.
[ Parent | on HN ]
Re:Show HN: I built a tiny LLM to demystify how language mod... by amelius on Monday April 06, 2026 @08:39AM (#47660136)
Ok. This makes me wonder about a broader question. Is there a scientific approach showing a pyramid of cognitive functions, and how many parameters are (minimally) required for each layer in this pyramid?
[ Parent | on HN ]