Making LLMs hallucinate less, how to diagnose ML models, from PM in Google AI to CEO of Galileo - Vikram Chatterji - The Data Scientist Show #066
The Data Scientist Show - Daliana Liu
00:00
Galileo for NLP and Computer Vision: A Diagnostics and Explainability Layer
LLM studio has created a new tool called Galileo for NLP and computer vision models. It automatically detects mislabeled samples and label over labs which dramatically reduces the amount of time it takes for data scientists to diagnose what's going wrong with the model in the R&D phase. And so you can manage your prompts figured out if they're hallucinating or not collaborate with your colleagues as well as fine-tune your data and debug the data that you're fine-tuning in the same productas well as monitor your LLMs in production.
Transcript
Play full episode
