Contents
The problem
The first attempt wasn't enough
What closed the gap
Where the value was
Vibe-coding a small gradient descent tool with Claude forced me to nail down exactly what I only half-understood from fast.ai.
Contents
The problem
The first attempt wasn't enough
What closed the gap
Where the value was

SERIES: Learning RL and JAX in Public - from zero to DeepMind :) On Day 1 I covered what JAX...

Every model you have heard of is trained by one algorithm, gradient descent. The idea is a ball rolling downhill to the lowest…

I tried Vibe Coding with Claude Code for about three weeks on a side project, and the result is...

A solid screenshot-to-BRD workflow for vibe coders, the two failure modes nobody talks about, and the missing step that separates…

You generated a feature in thirty seconds using Claude. It compiled. You deployed it. Then something...

- The Setup I've been working on a semantic recall application called VaultAI for AI tools and...