Evidence item

NVIDIA describes test-time scaling as applying more inference compute to improve AI accuracy on complex problems. DIRECT_TEXT

Authenticity UNVERIFIED · extraction UNVERIFIED · independence group none (unreviewed) · created seq 10187

Source: How Scaling Laws Drive Smarter, More Powerful AI · locator {} · excerpt hash sha256:2cde28c4f25515ef45ff856ab0526b24739c9e40894039910978ed2854c6cbef

The recent rise of test-time scaling — applying more compute at inference time to improve accuracy — has enabled AI reasoning models, a new class of large language models (LLMs) that perform multiple inference passes to work through complex problems.