Worse! It's trained to output coherent reasoning, so by putting the assumption l... | Hacker News

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

		kqr 4 days ago \| parent \| context \| favorite \| on: I want to wash my car. The car wash is 50 meters a... Worse! It's trained to output coherent reasoning, so by putting the assumption last there's a risk it massages the assumption slightly to fit the conclusions it has already drawn.

		help

cracki 4 days ago [–]

That's a real danger, yes.

If it's the reasoning kind, then it'll run through one iteration in the background before it composes its emissions for the meatbag.

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