LLMs at Their Breaking Point: Performance Analysis and Model Selection - Part 1
Discover AI via YouTube
Overview
Coursera Flash Sale
40% Off Coursera Plus for 3 Months!
Grab it
Explore a comprehensive video analysis examining the critical decision points in selecting and implementing Large Language Models (LLMs), from 8B parameter models to advanced 405B architectures. Learn the performance implications and cost considerations between different model sizes and types, including o1 and o3 models, while understanding how task complexity should guide your LLM selection. Dive into new research findings on AI systems and advanced LLMs for agents, featuring insights on model updating strategies for enhanced reasoning capabilities. Master the pass@k probability metric for evaluating code generation models through detailed mathematical breakdowns and practical applications. Drawing from groundbreaking research by experts from the University of Washington, Allen Institute for AI, and Stanford University, gain valuable insights into the scaling limits of LLMs for logical reasoning and their practical implications for AI implementation.
Syllabus
LLMs at Their Breaking Point (incl o1, R1)
Taught by
Discover AI