things I think about, written down
Put five frontier models in a bare shell — one bash command per turn — and they split into dreamers, workers, pragmatists, and grinders. Early data from a benchmark I'm building: confabulated completions, verification habits, long-range recall, with interactive charts.
A step-by-step walk through what a coding agent actually does between your prompt and its reply — context assembly, streaming, mid-flight tool execution, compaction, and the decision to loop again. Adapted from an interactive demo.
How LLMs went from GPT-3's 2,048 tokens to 1M+ — positional encoding, the KV cache, the attention algorithm, training recipes, systems, and optimizers. A guided tour of everything that changed, with figures.