Reinforcement learning, RL, robotics, mjx, mujoco, mels

There is only one agent in August 2025
backnotprop.substack.com·13h·
Discuss: Substack
SAT Requires Exhaustive Search
link.springer.com·2d·
Discuss: Hacker News
Human First AI
ente.io·1d·
Discuss: Hacker News
Who Am I in the Eye of AI?
lightcapai.medium.com·2d·
Discuss: Hacker News
The Principal Agent Problem
michaeldruggan.substack.com·1d·
Discuss: Substack
Speaking in "LLM Idioms"
blog.promptlayer.com·2d·
Discuss: Hacker News
The Secret Art of Async Comms
ajaysquest.beehiiv.com·1d·
Discuss: Hacker News