Compact computers can now run surprisingly large language models locally. But fitting a model into memory is not the same as running it quickly, and advertised NPU TOPS are a particularly poor substitute for measured LLM throughput.

This comparison focuses on single-user local inference and coding …

The conversation around LLM wikis needs to shift.

Andrej Karpathy’s original LLM Wiki gist describes something interesting: a persistent, compounding artifact maintained by an agent through three operations — ingest, query, lint. Raw sources flow in. The wiki absorbs them, cross-links them, …

AI tools might be the most powerful discovery engines we’ve ever built.

Lately I’ve been thinking about something curious.

When developers use AI coding tools like OpenAI Codex or Claude Code, the workflow often looks like this:

idea → prompt → generated code → tweak the prompt → try …