Building LLM Apps & the Challenges that come with it. The What's AI Podcast Episode 16: Jay Alammar
What's AI Podcast by Louis-François Bouchard
Preference Training in Machine Learning
The training, this is the learning in machine learning of making a prediction and updating the model based on how wrong that prediction was. This step is what happens billions of, or millions of billions of times. And then you can get a little bit more, you can align the model better to those behaviors by having another sort of training step which sometimes can include re-en re-reward model. That complexity, I think a lot of people don't need to get it, like as long as you understand the language modeling objective and then this, the idea of preference, that gets you most of the understanding that you need.
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.
