Overview
Save Big on Coursera Plus. 7,000+ courses at $160 off. Limited Time Only!
Explore the differences between safety in traditional internet search and GPT search in this 26-minute video from Trelis Research. Gain a simplified understanding of LLM and GPT training processes, and delve into the concept of "alignment" in AI development. Learn why careful data selection for model training may be a more effective approach to AI safety than alignment strategies. Discover insights into the complexities of AI language model safety and development in this accessible guide.
Syllabus
An Overly Simple Guide to AI LLM Safety
Taught by
Trelis Research