misc
an archive of posts in this category
Feb 08, 2025 | Why you should write Jax functions without broadcasting |
---|---|
Feb 08, 2025 | grpo_server: GRPO for fun and agents and profit |
Feb 01, 2025 | Prediction: source code is going the way of assembly language |
Jan 27, 2025 | Smol models can add (better). First experiment in LLM finetuning |
Jan 17, 2025 | The mypy bug that just kept on giving |
Jan 07, 2025 | Getting into coding with LLMs; Nebius onboarding is lovely |