how would you do it? | Hacker News

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

		WithinReason 8 months ago \| parent \| context \| favorite \| on: Scaling up test-time compute with latent reasoning... how would you do it?

nielsole 8 months ago [–]

my naive way would be to try to do seq2seq with the hidden state as input. Not sure how to replace the supervised samples though.

WithinReason 8 months ago | [–]

OK but what would you use as ground truth?

Consider applying for YC's Winter 2026 batch! Applications are open till Nov 10
Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact