reinforcement-pretraining. Implementation of Reinforcement Pre-Training (RPT) for Language Models - ArXiv:2506.08007
22contextS. contextSmart.
19Claude-4-coding-projects. A collection of fun simple coding projects (mostly games) I made to test the new Claude models.
2work-together. Multi agent system that lets agents work together
2ProCreations-Official. Config files for my GitHub profile.
1