DRawson5570/linguistic-rl-scheduling
A new paradigm for AI: Compressing wisdom, not just scaling parameters.
2 best points · 2 comments · 3 Hacker News posts · 0 GitHub stars · View on GitHub
Hacker News discussions
- Show HN: Linguistic RL – A 7B model discovers Occam's Razor through reflection (2 points, 0 comments, by drawson5570, 2025-11-07)
- Linguistic RL: 3B Models Exceed 100B Performance (86% vs. 81%) (2 points, 1 comments, by drawson5570, 2025-11-12)
- Show HN: Framework for Transferring AI Capabilities (Students Surpass Teachers) (1 points, 1 comments, by drawson5570, 2025-11-10)