It can't truthfully answer "why" questions, only infer them in a way that aligns... | Hacker News

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

		joquarky 13 days ago \| parent \| context \| favorite \| on: Claude Fable 5.1 and Claude Mythos 5.1 It can't truthfully answer "why" questions, only infer them in a way that aligns with its training for conversational engagement.
		help

dpkirchner 13 days ago [–]

Of course, that's how LLMs work. It's still amusing, at least to me.

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