$ grep --tag "ai"

#ai (2)

#ai#prompts#llm

Prompt patterns I actually reuse

Rubric-first grading, negative few-shot examples, and chain-of-verification — the only three patterns I trust in production.

Aug 4, 2026 · 3 views

#ai#javascript#teaching

Shipping a Tiny LLM Playground in the Browser

A 40-line browser playground that makes softmax, sampling and temperature visible — with runnable code right in the post.

Aug 4, 2026 · 1297 views