Re:Amazon saves millions by replacing Sonnet 4.6 with Strand...
by nixon_why69 on Tuesday November 10, 2026 @05:48AM
(#50438486)
Yeah but they're all trained together along with their gate tensor. Evaluating a moderate length prompt pulls in most/all of them.
Does it? All the latest frontier models that have made technical details publicly available are using MoE; smaller specialized units that work together.