LLM Debugging Techniques
Andriy discusses using Atlas to debug LLM hallucinations by mapping bad inputs. He explains how biasing input data can manipulate LLM behavior. Jacob explores the future of GPT for all amid other open source model releases.In this clip
From this podcast
Unsupervised Learning
Ep 17: Nomic AI Co-Founder Andriy Mulyar on "GPT-4-All", LLMs in Video Games, and Apple's AI Strategy
Related Questions