Sign in

sean-mcleish.bsky.social

@sean-mcleish.bsky.social
5 followers 4 following 0 posts
PostsRepliesMedia
Reposted by @sean-mcleish.bsky.social
tomgoldstein.bsky.social @tomgoldstein.bsky.social · 10/02/2025
New open source reasoning model! Huginn-3.5B reasons implicitly in latent space 🧠 Unlike O1 and R1, latent reasoning doesn’t need special chain-of-thought training data, and doesn't produce extra CoT tokens at test time. We trained on 800B tokens 👇
1124
Reposted by @sean-mcleish.bsky.social
Jonas @jonasgeiping.bsky.social · 10/02/2025
Ok, so I can finally talk about this! We spent the last year (actually a bit longer) training an LLM with recurrent depth at scale. The model has an internal latent space in which it can adaptively spend more compute to think longer. I think the tech report ...🐦‍⬛
1267