Eugene Vinitsky 🦋
@EugeneVinitsky
Linear complexity and growing memory; another wacky exciting result from @percepta
Christos Tzamos@ChristosTzamos · Oct 2LLMs don’t need retraining to become more capable.
Our new architecture, Spotlight, gives AI models growing memory, allowing them to gain knowledge and capabilities without changing their weights.
Token generation takes constant work, no matter how much information is stored.
Our new architecture, Spotlight, gives AI models growing memory, allowing them to gain knowledge and capabilities without changing their weights.
Token generation takes constant work, no matter how much information is stored.
0:24 2 99