The Relative Adoption Metric normalizes downloads by model size and by time, scaled so a score above 1 means a model is on pace to become one of the ten most-downloaded models ever in its size class. One number, messy landscape.
The ATOM report tracks GPT-OSS's rise, inferenceRunning a trained model to get answers — the phase where AI is actually used, as opposed to trained.Full definition → market share, and the pull of China's mid-tier labs — Moonshot, Z.ai, MiniMax — arguing much of the open-model contest is being decided below the frontier tier.
TurnWise measures the gap between single-turn and multi-turn ability: models that look strong on one-shot benchmarks degrade across a conversation, and the paper covers how to build training data that closes it.
Most RL on language models is on-policy but naive — the model learns from recent attempts in its weights, not in its context windowThe maximum amount of text a model can consider at once — its working memory for the current conversation or task.Full definition →. The meta-RL search paper feeds prior rollouts back in as context so later attempts inherit what earlier ones found.
Terms in this piece · Glossary
RLHF — Reinforcement learning from human feedback — training a model to prefer answers humans rate as better, which turns a raw text predictor into a usable assistant.
alignment — The work of making AI systems actually pursue what their builders and users intend, rather than something subtly or dangerously different.
inference — Running a trained model to get answers — the phase where AI is actually used, as opposed to trained.
context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
Why it matters
If you're moving from prompting into actually shaping model behavior, this pairs a professionally edited RLHFReinforcement learning from human feedback — training a model to prefer answers humans rate as better, which turns a raw text predictor into a usable assistant.Full definition → book with a free structured lecture course covering post-training from foundations to modern RL algorithms — a rare end-to-end path into LLM alignmentThe work of making AI systems actually pursue what their builders and users intend, rather than something subtly or dangerously different.Full definition → rather than scattered blog posts.
Key quotes
“The RAM score is designed so that a score >1 indicates a model is, at that point in time, on track to be a top 10 most downloaded model of its size category, ever.”
“The goal of this book was to write the book I wished I had when I was getting started in post-training language models.”
“Research is the only early warning of some big changes coming.”
