Re:Tencent's 'Hunyuan-T1'–The First Mamba-Powered Ultra-Larg...
by seattleeng on Sunday March 23, 2025 @02:43PM
(#43454854)
It’s more like conditioning the posterior of a response on “Ok, so…” lets the model enter a better latent space for answering logically vs just spitting out a random token.
[ Parent
| on HN ]
There are no comments on this comment yet.