The weighting mechanism that lets a model decide, word by word, what other information matters most right now.
AI History
+4
Aug 31, 2026
•
2 min read
In the summer of 2014, a graduate student in Montreal built a fix for a stubborn bug in a translation model, one that would outlive the paper it was written for. He didn't call it attention. For a while, neither did his supervisor.
