跳到正文
@kimmonismus· @kimmonismus · X·· 2026-09-03AI 评分27
AI 导读

753B 模型读题:4B 模型写答案。 Mostik 报告称,其潜在桥接让 4B 模型将与大模型的性能差距缩小了一半。 桥接组合的计算量比得分相当的中等规模模型少 2.5 倍。 这是对当今大多数多模型系统所用基于文本的交接方式的一个迷人替代方案。太惊人了!

正文

A 753B model reads the problem: A 4B model writes the answer.

Mostik reports that its latent bridge lets the 4B model close half the performance gap to the 753B model

The bridged pair uses 2.5x less compute than a score-matched mid-sized model

A fascinating alternative to the text-based handoffs used by most multi-model systems today. Incredible!

来源:@kimmonismus · x.com