Onto the next: experiments and notes on machine learning, LLMs, and reinforcement learning.https://rhaque.dev/https://rhaque.dev/blog/gan-from-scratch/https://rhaque.dev/blog/gan-from-scratch/Two tiny networks, hand-written backprop, and a ring. What a 2-D GAN makes visible that image GANs hide, including why a falling loss is bad news.Thu, 23 Jul 2026 00:00:00 GMThttps://rhaque.dev/blog/hello-world/https://rhaque.dev/blog/hello-world/Why I built this, and what I'll share here: machine learning, frontier LLM research, reinforcement learning, and interactive experiments.Wed, 22 Jul 2026 00:00:00 GMThttps://rhaque.dev/blog/edge-of-stability/https://rhaque.dev/blog/edge-of-stability/A tiny gradient-descent toy and what it shows about learning rates.Mon, 20 Jul 2026 00:00:00 GMT