Researchers find why larger language models pick up skills that small ones miss

Y	Hacker News new \| ask \| show \| jobs

	Researchers find why larger language models pick up skills that small ones miss (the-decoder.com)
	4 points by maxloh 7 days ago

1 comments

masking 7 days ago

I for one can’t wait to see a 1.2b, 2b, or 3b model use skills. It would democratize the agentic AI landscape. My 4b model is to slow on my M1Pro. Need quicker access to standardized skills and tool usage.

link