GPT Reviews
Google DeepMind's new AI tool that generates video soundtracks by combining text prompts with visual content.
Challenges of building large training AI clusters, including power, network topology, and reliability.
How large language models acquire factual knowledge during pretraining and their probabilistic reasoning capabilities.
LLARVA's vision-action instruction tuning that enhances robot learning.
Contact:Β Β sergi@earkind.com
Timestamps:
00:34 Introduction
01:47Β Google DeepMindβs new AI tool uses video pixels and text prompts to generate soundtracks
05:22Β Large language model data pipelines and Common Crawl (WARC/WAT/WET)
06:47 Fake sponsor
08:20Β How Do Large Language Models Acquire Factual Knowledge During Pretraining?
10:01Β What Are the Odds? Language Models Are Capable of Probabilistic Reasoning
11:22Β LLARVA: Vision-Action Instruction Tuning Enhances Robot Learning
13:06 Outro