Hacker News new | ask | show | jobs
user: fchaubard
created: 2013-10-07
karma: 11

submissions:

LLMs are NOT Turing Complete (at train time), we need "train time recurrence"
2 points | 0 comments
0 points | 0 comments
0 points | 0 comments
Scaling RNNs to Billions of Parameters with Zero Order
7 points | 3 comments
0 points | 0 comments
0 points | 0 comments
0 points | 0 comments
0 points | 0 comments
0 points | 0 comments
0 points | 0 comments
0 points | 0 comments