# Entropic Musings This is a blog where I will post stuff that fascinates me. Each blog post is alive and will be iterated over many times. ### Note: I am currently working at CamelAI, setting up the infra to do RLVR effectively. The blog is thus currently paused. ## 📖 technical blogs: - [[latro|Latent Reasoning Optimization (LaTRO)]] - [[the rl for deepseek-r1|The RL used for Deepseek-R1]] - [[rlvr terminology|How I think about the RLVR primitives]] ## 🏗 Coming some day - **Blog Posts**: - PRIME: Getting PRMs for free from ORMs - Getting up to speed with Multi-Agent RL ___ If you wanna contact me, dm me on *𝕏*: [@hallerite](https://www.x.com/hallerite)