https://angelraychev.com/ https://angelraychev.com/a-generalization-of-descent-polynomials/2026-10-24 https://angelraychev.com/distributed-agent-training-and-evaluation/2026-10-21 https://angelraychev.com/explicit-versus-learned-search/2026-10-23 https://angelraychev.com/four-arm-polyominoes/2026-09-14 https://angelraychev.com/four-levers-and-a-trap/2026-09-09 https://angelraychev.com/from-software-work-to-specialized-agents/2026-10-21 https://angelraychev.com/model-specialization-and-training-agents/2026-10-23 https://angelraychev.com/nutrition-notebook/2026-10-10 https://angelraychev.com/running-makes-the-city-smaller/2026-10-10 https://angelraychev.com/running-notebook/2026-11-02 https://angelraychev.com/scalable-meta-learning-from-hindsight/2026-10-24 https://angelraychev.com/scaling-laws-for-generative-reward-models/2026-10-23 https://angelraychev.com/the-optimization-nobody-is-running/2026-10-10 https://angelraychev.com/what-should-a-running-workout-maximize/2026-10-10 https://angelraychev.com/princess/2026-09-13 https://angelraychev.com/cop-prisoner/2026-10-23