Experimental 3.5T K2 merge beats GPT-4.5 and Opus at writing | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		Experimental 3.5T K2 merge beats GPT-4.5 and Opus at writing (huggingface.co)
		2 points by bo0tzz 56 days ago \| hide \| past \| favorite \| 1 comment

mynti 56 days ago [–]

"beats at writing" is kind of far fetched since the page provides three generic pormpts with answers from Opus, GPT5 and K3. But a 3.5T model is crazy huge and the answers still feel more or less the same to the other models

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact