Optimize any text — prompts, code, agent architectures, configurations — using LLM-based reflection and Pareto-efficient evolutionary search. If you can measure it, you can optimize it.
This talk is about separating the task, the job to be done, from the implementation details: the model, harness, tactics, and other elements that are constantly changing.
RL-training Qwen 3.5 35B to make watercolour images by writing p5.brush sketches — and what collapsing a nine-signal reward rubric into four pairwise-judged ones did to training.
Agent skill for beautiful, verifiable architecture, workflow, sequence, data-flow, and lifecycle diagrams—self-contained HTML with motion and crisp export.
A catalogue of 49 AI writing tells, each with a plain rewrite, shared by Fireside. Drop it into a system prompt to stop LLM output reading like LLM output.
🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman
An occasional email when notable AI dev tools and models land in the directory. No spam, unsubscribe anytime.