Neural Pensieve

Sunrise over Mt.

Policy gradient methods are like climbing a treacherous terrain to find the highest peak.

Hokm is a 4-player Persian card game similar to Bridge, and the robot is learning it by playing against younger versions of itself!

TL;DR: I trained small LLMs like GPT-2 to play text-based games using reinforcement learning (PPO) on my budget GPU.

The first time I heard about how diffusion models work, I was dumbfounded!

Running reinforcement learning (RL) experiments—especially when implementing models yourself—is notoriously more challenging than typical supervised learning (SL) experiments (as attested by none other than Andrej Karpathy here).

A few years back, I started wondering: what’s the minimum number of questions you’d need to ask someone to figure out the size of their vocabulary?

With the rapid rise of Generative AI and its growing influence, humanity is entering an era of uncertainty, particularly concerning AI’s negative impact on society.