Is scaling all you need for AI Large Language Models? Scaling laws and the Inverse Scaling Challenge. Featuring Ian McKenzie, FAR AI Research Scientist
Orchestrate all the Things
00:00
The Criteria for Evaluating Language Models
CNN's John Sutter looks at the criteria that were used to evaluate data submitted for a new study on language models. The six-criteria set includes inverse scaling strength, task importance and novelty. It also asks how well does the data set represent the idea that you're trying to demonstrate. And related to this one is the reproducibility, like if someone else were to try to follow along and make a similar data set to yours,.
Transcript
Play full episode
