Test-time Compute & Reasoning
The 2024 discovery: models get smarter by thinking longer.
Stai visualizzando una scheda concettuale: cosa significa questo termine in linguaggio chiaro, e i record che mette in relazione.
Reasoning models produce long internal chains of thought before answering, and accuracy scales with how much compute they spend thinking — a new scaling axis alongside model size and data. o1 introduced it; R1 open-sourced it; every frontier model now has a thinking mode. The infrastructure consequence is enormous: a single hard question can cost thousands of times more tokens than a chat reply, shifting demand from training clusters to inference fleets.
Come si collega al resto dello stack
I collegamenti di questa scheda a colpo d'occhio — clicca un gruppo per raggiungerlo.
Base per
Correlati
Fonti
Record revisionato al 2026-01-15 — vedi Metodologia.