728: Use Contrastive Search to get Human-Quality LLM Outputs

Learn how to achieve human-like outputs from LLMs in this week’s Five-Minute Friday with Jon Krohn. Understand the various current methods available to decode and generate text, as well as the differences between them. Find out about greedy search, beam search, sampling, and contrastive search, and how you can use them to create incredibly useful LLMs. Additional materials: www.superdatascience.com/728 Interested in sponsoring a SuperDataScience Podcast episode? Visit JonKrohn.com/podcast for sponsorship information.

Om Podcasten

The latest machine learning, A.I., and data career topics from across both academia and industry are brought to you by host Dr. Jon Krohn on the Super Data Science Podcast. As the quantity of data on our planet doubles every couple of years and with this trend set to continue for decades to come, there's an unprecedented opportunity for you to make a meaningful impact in your lifetime. In conversation with the biggest names in the data science industry, Jon cuts through hype to fuel that professional impact. Whether you're curious about getting started in a data career or you're a deep technical expert, whether you'd like to understand what A.I. is or you'd like to integrate more data-driven processes into your business, we have inspiring guests and lighthearted conversation for you to enjoy. We cover tools, techniques, and implementation tricks across data collection, databases, analytics, predictive modeling, visualization, software engineering, real-world applications, commercialization, and entrepreneurship − everything you need to crush it with data science.