Hacker News
- GPU Restaking – Beyond digital currencies to physical computing resources https://blog.bagel.net/p/gpu-restaking 6 comments
- I reversed engineered how WizardMath actually works. The 3-step process is brilliant. [Technical Analysis] https://blog.bagel.net/p/train-fast-but-think-slow 3 comments deeplearning
- Pattern Matching != Reasoning: We analyzed 2 distinct paths to make LLMs actually think [Technical Deep Dive] https://blog.bagel.net/p/train-fast-but-think-slow 17 comments learnmachinelearning