
Artificial Intelligence & Large Language Models: Oxford Lecture — #35
Manifold
The Importance of Attention in Open AI
The jump from GPT three or 3.5 to GPT four, which just happened in the last, I mean, they only released GPT four in the last month or so, shows like really qualitative differences in performance. So it's very, very important information. Like, like, open AI would very much not like it if someone stole these matrices from them and like released them on the internet. Okay. And this attention mechanism compares Xi to Xj, but only after making a basis change using the Q matrix and the K matrix. That's the magic sauce that's in these transformer models is these things. okay.
00:00
Transcript
Play full episode
Remember Everything You Learn from Podcasts
Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.