This is very interesting. I don't see much discussion of interpretability in day... | Hacker News

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

		pbmango 17 hours ago \| parent \| context \| favorite \| on: Show HN: Steerling-8B, a language model that can e... This is very interesting. I don't see much discussion of interpretability in day to the day discourse of AI builders. I wonder if everyone assumes it to either be solved, or to be too out of reach to bother stopping and thinking about.

		help

adebayoj 12 hours ago [–]

Most interpretability techniques haven't yet to be shown to be useful for everyday model pipelines. However, the field is working hard to change this.

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