Stories by gpjt

Writing an LLM from scratch, part 17 – the feed-forward network

Writing an LLM from scratch, part 16 – layer normalisation

Leaving PythonAnywhere

Writing an LLM from scratch, part 15 – from context vectors to logits

Writing an LLM from scratch, part 14 – the complexity of self-attention at scale

Writing an LLM from scratch, part 13 – attention heads are dumb

Writing an LLM from scratch, part 12 – multi-head attention

Writing an LLM from scratch, part 11 – batches

The Business of the AI Labs

Writing an LLM from scratch, part 10 – dropout

Adding /Llms.txt

Writing an LLM from scratch, part 9 – causal attention

Writing an LLM from scratch, part 8 – trainable self-attention

It’s still worth blogging in the age of AI

The benefits of learning in public

Ask HN: If you have a blog, do you have an RSS feed?

Do reasoning LLMs need their own Philosophical Language?

LLM Quantisation Weirdness

PythonAnywhere: Our Commitment to Providing Free Accounts

Pam-unshare: a PAM module that switches into a PID namespace