Who am I?

All, yet none of these:

• Software engineer
• AI researcher
• Startup founder
• YouTuber... 🤦‍♀️

If you really want to stalk me:

Why did I make this?

Because I'm intrigued by difficult things. On a first encounter, diffusion models seem extremely complicated. When you read a paper, the math checks out, but you're left wondering whether this overhead is truly needed.

Even though I do have an engineering and AI research background, I came to the diffusion field as a complete outsider. I had really basic stupid questions to ask. Hopefully that makes this material more approachable.

My AI pledge

The time you spend reading my content is just as valuable as my time writing it. So I will never feed you AI slop. For transparency, here is how I use AI:

• Researching and understanding
• Writing animation code
• Final pass to refine or compress my (hand-written) text

Tips

• I recommend using Atlas or Comet and ask questions about the content right from the browser.
• You can also watch this video for an end-to-end overview, or check out the entire playlist.
• But ultimately, you can only benefit so much for spoon feeding. Once you gain some confidence, you should read the foundational papers.

Feedback

I really want to hear feedback from you:

• What's clear or unclear?
• What adjacent topics you'd like covered?
• Are there any mistakes?

If your contributions lead to a meaningful improvement, I'll make sure to credit you and link to your socials.