Shows a diffusion LM that spends variable compute per tokenThe chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.Full definition → via recurrent loops and a learned halting policy, with tunable thresholds trading refinement against parallel decoding speed. Weights are CC-BY-NC, so useful for research and evaluation, not production.
Terms in this piece · Glossary
LLM — A large language model — the neural network behind tools like Claude and ChatGPT, trained on huge amounts of text to predict what comes next.
transformer — The neural network architecture behind modern AI models, built on attention — letting every word directly consider every other word in parallel.
token — The chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.
inference — Running a trained model to get answers — the phase where AI is actually used, as opposed to trained.
