DraganSr

web-links (blinks) web-log (blog) by Dragan Sretenovic

Tuesday, March 17, 2026

Visualizing AI training & thinking

scientific paper, vs hacking projects

 Visualizing the Chain of Thought in Large Language Models


microgpt visualizer https://microgpt.boratto.ca/

B44ken/microgptn @GitHub
a tiny visualization of a GPT model, running locally in the browser.


microgpt //karpathy.github.io/2026/02/12/microgpt/

enescang/microgpt-visualizer: Interactive visualization of a minimal GPT implementation with autograd engine.

MicroGPT Visualizer

Show HN: Microgpt is a GPT you can visualize in the browser | Hacker News

Understanding and Coding the Self-Attention Mechanism of Large Language Models From Scratch | Sebastian Raschka, PhD




Dragan at 8:32 PM

No comments:

Post a Comment

‹
›
Home
View web version

About Me

My photo
Dragan
View my complete profile
Powered by Blogger.