my naive way would be to try to do seq2seq with the hidden state as input. Not s... | Hacker News

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

		nielsole on Feb 11, 2025 \| parent \| context \| favorite \| on: Scaling up test-time compute with latent reasoning... 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 on Feb 11, 2025 [–]

OK but what would you use as ground truth?

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