
Monthly Roundup: New LLMs, GTC 2024, Constraint-Driven Innovation, Model Safety, and GraphRAG
The Data Exchange with Ben Lorica
Efficiency Improvements and Large Scale Models
Exploring advancements in algorithm efficiency and data preparation, with a focus on optimizing data, synthetic data creation, and training process enhancements. Discussion on the potential for models to become more efficient over time, along with insights on training large models like a 200 billion parameter LLM with a training set of four trillion tokens and the associated infrastructure and costs.
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.