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
Is There a Scaling Challenge for Large Language Models?
Ian Mackenzie is a research scientist at FAR AI, an organization interested in AI alignment. He's part of the team organizing the inverse scaling challenge to improve large-language models and how they are trained. As you increase the amount of data that you use to train these models, as you increase the size of the models, the performance gets predictably better says Mackenzie.
Transcript
Play full episode
