hallucinations decrease with scale and reasoning, the model just gets better and... | Hacker News

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

		whimsicalism 12 months ago \| parent \| context \| favorite \| on: How has DeepSeek improved the Transformer architec... hallucinations decrease with scale and reasoning, the model just gets better and stops making stuff up.

littlestymaar 12 months ago | [–]

o1 still hallucinates badly though.

Jerrrry 12 months ago | [–]

False, facts only need to be seen once, and one mis-step in reasoning and your CoT is derailed.

whimsicalism 12 months ago | [–]

> one mis-step in reasoning and your CoT is derailed.

tell me you've never seen reasoning traces without telling me

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