transformer
machine-learning model architecture first developed by Google Brain
Episodes
-
#5774: Reading the Model's Mind Mid-InferenceWhat if you could watch a model decide? Inside the tools that open up inference mid-computation — and the limits they hit. -
#5188: DeepSeek's Point Release That Isn'tDeepSeek shipped a whole new architecture and called it a point release. Here's what actually changed inside the model. -
#5396: Teaching a Small Model to Stop Spelling Out NumbersYour ASR pipeline is fine until someone dictates "three point two" and gets "three point two" spelled out. Here's how inverse text normalization ac...