LATEST: EPISODE 042

Bridging the gap from
Simulation to Reality

Deep dives into Reinforcement Learning, Embodied AI, and the engineering challenges of AGI. No hype, just signal.

Latest Episodes

VIEW ARCHIVE ->
EP 042 • NOV 20

Scaling On-Policy RL for LLMs

We discuss the shift from supervised fine-tuning to reinforcement learning with environmental feedback.

#RLHF #PPO
EP 041 • NOV 14

Agentic Operating Systems

Exploring how agents will interface with traditional OS layers and the privacy implications.

#Agents #Infra
EP 040 • NOV 07

Zero Knowledge Proofs in AI

Can we prove model weights without revealing them? A crossover episode.

#ZKML #Privacy