I published a LoRA fine-tuning run two weeks ago. The headline was that my first test set had lied to...
A reader read my benchmark better than I did
I published a LoRA fine-tuning run two weeks ago. The headline was that my first test set had lied to...
One file the agent must read, one it must pass, one it must stay inside. An afternoon of work, and the oversized diff fails before review.
Your AI doesn't read your prompt word for word. It reads tokens. In this episode of Prompt Pad,...
Claude Code sent 74,500 tokens with my first message of the day, before it had read a single word I...