Content tagged with "machine learning" (5)
All content across blogs, linklog, and books with this tag.
Links
- by Andrej Karpathy
You implement backprop, attention, and a GPT from scratch with no frameworks, and by the end you actually understand what the machine is doing instead of just calling library functions.
- by Andrej Karpathy
Karpathy's dense, opinionated survey of everything that changed in language models over 2025, written by someone who has built these systems himself.
- by Jay Alammar
The clearest visual explanation of how Transformers actually work, from self-attention to positional encodings, now referenced by courses at Stanford, Harvard, and MIT.
- by Andrej Karpathy
Karpathy builds an autograd engine from nothing, one line at a time, until backprop is something you could re-derive yourself instead of a formula you take on faith.
- by Anthropic
Anthropic's interpretability team looks inside the model and catches it planning several words ahead and reasoning in a concept space shared across languages.