Microsoft unveils MAI-Base-2, a MoE model with 2.8T total and 80B active parameters, claiming 4x-12x more pretraining FLOPs-efficiency than DeepSeek-V4-Pro-Base
microsoft.ai via Techmeme
In June, we announced MAI-Thinking-1, a general-purpose foundation model post-trained on top of MAI-Base-1 with strong reasoning performance.
A short brief from Techmeme’s public feed, in the source language. The full original article has not been read.
More from Techmeme
Outside of tech there has been no financial payoff to US companies for using AI, now viewed as a margin-hurting cost center, as VC-backed firms burn more tokens
Techmeme 4 h ago
Source: Replit recently moved most AI spend from Anthropic to OpenAI, which gave 30%+ off in a deal worth $100M+/year, after Anthropic discontinued its discount
Techmeme 6 h ago
A look at Alpha School, a network of private schools that claims to teach kids 2x as fast using AI; data shows ~50% of K-8 students missed this goal in math
Techmeme 8 h ago
An interview with Ciena CEO Gary Smith, a veteran of the 2001 telecoms crash, on AI demand outpacing supply for Ciena's optical networking chips, and more
Techmeme 10 h ago