01 4 posts · 22 min
Eric Eaglstun · On AI
A working notebook on AI & machine learning.
Almost nobody fully understands how modern AI works, not even the people building it. That makes it easy to fear, easy to hype, and hard to think clearly about.
I started this to fix that for myself, and then figured it might help anyone else trying to make sense of AI. The heart of it is a glossary - short, plain-language definitions of the terms I kept tripping over while running models on my own machine, explained the way you’d explain them to a friend. Around it sit practice notes, blog posts, and deep dives into the machinery underneath. No hand-waving: because you can’t have a sane opinion about something you don’t understand.
Latest
- practice The Browser Doesn't Need a Loading Screen for the Loading Screen
My Dillo fork brings native Mac controls and an iOS port to a small browser with its own rendering engine and no JavaScript. AI helped build it; deciding how much browser I wanted was my job.
- deep dive I Taught It to Draw. It Learned to Comply.
A fine-tuning post about the thing nobody warns you about: every category you add teaches a behavior and also teaches a shape, and the shape does not stay in its lane. Eleven joke rows about drawing a cat produced six out of six working code samples. Twenty-four rows of small talk taught terse agreement, which leaked verdicts onto yes/no questions. Both causes were invisible in the category that caused them.
- blog Be Nice to the Toaster
Starting November 12, sustained and pointless cruelty toward Claude breaks Anthropic's rules. People are rolling their eyes. I think it's one of the best calls they've made all year, and it has nothing to do with whether the thing can feel anything.
Pick a thread
The site makes more sense as a few arguments than as one long reverse-chronological pile.
02 3 posts · 26 min
Why does the machine sound so certain?
03 3 posts · 24 min
What does local AI actually take?
Blog →
Notes and posts on AI/ML - local inference, models, and whatever I’m tinkering with.
Practice →
How I actually use AI day-to-day, and the techniques that have earned a permanent place in my workflow.
Deep Dives →
Longer, hands-on walkthroughs - how the pieces fit together, with the details left in.
Glossary
All 53 terms →Short, plain-language definitions of the AI/ML terms I keep bumping into - formats, GPU backends, architectures, and the concepts underneath.