Re:The bigger-is-better approach to AI is running out of road
by n4r9 on Sunday June 25, 2023 @06:43AM
(#36466829)
All of this seems possible in a deterministic system which evaluates whether or not to retain a piece of information based on past experience.
[ Parent
| on HN ]
Re:The bigger-is-better approach to AI is running out of road
by circuit10 on Sunday June 25, 2023 @06:58AM
(#36466902)
LLMs can be deterministic too at temperature 0
Re:The bigger-is-better approach to AI is running out of road
by williamtrask on Sunday June 25, 2023 @07:07AM
(#36466949)
But they don’t work very well at temp 0. Better to seed your random numbers.