Nothing here yet.
Nothing here yet.
Mar 22 · 18 min read · I recently set out with a specific goal: I wanted to build an AI agent that could truly understand a massive, undocumented codebase. If you’ve ever tried to feed a codebase into a standard Retrieval-A
Join discussion
Mar 7 · 4 min read · We finally made it. If you have been following this "learning in public" series from the beginning, we have been deep in the trenches of PyTorch tensor shapes. We’ve built Supermarket Embeddings, inje
Join discussion
Mar 7 · 4 min read · If you’ve been following my "learning in public" series, we’ve spent the last few posts in the trenches. We’ve wrestled with tensor shapes, built mathematical blindfolds (Masked Self-Attention), bridg
Join discussion
Mar 6 · 5 min read · If you’ve been following this "learning in public" PyTorch series, we have successfully built the entire Transformer Encoder. We gave it a sentence, mapped it to embeddings, added spatial awareness, a
Join discussion
Mar 5 · 7 min read · If you’ve been following my PyTorch "learning in public" series, we’ve already tackled the hardest part of the Transformer architecture: Multi-Head Attention (MHA). We took our tokens, split them into
Join discussion
