Samuelm - Stardance

SL-LLM_R - A reproducible research prototype for verifier-grounded counterfactual LLM learning.
- 7 devlogs
- 213h
Building a LLM system that can learn from verified outcomes by replaying counterfactual choices, identifying what caused success or failure, and safely turning that evidence into future improvements.

Last updated 8 days ago
My awesome macropad!
Hardware
- 0 devlogs
- 0h
Last updated 29 days ago
Hackpad