Essays, paper notes, and project write-ups on machine learning by Shyam Pathak.https://shyampathak22.github.io/en-ushttps://shyampathak22.github.io/writings/what-we-owe-the-made/https://shyampathak22.github.io/writings/what-we-owe-the-made/On substrate, authorship, and the ontological crime of building intelligences we refuse to look at.Mon, 04 May 2026 00:00:00 GMTaiethicssubstratephilosophyhttps://shyampathak22.github.io/writings/adaptive-reward-weighting/https://shyampathak22.github.io/writings/adaptive-reward-weighting/On GDPO, adaptive reward weighting, and getting denser gradient signal out of multi-reward RL without inviting reward hacking.Sat, 28 Mar 2026 00:00:00 GMTrltrainingoptimizationgrpogdpo