784: Aligning Large Language Models, with Sinan Ozdemir

Aligning LLMs: How can we teach pre-trained LLMs to hold a conversation and learn new information from each other? This was where Sinan Ozdemir began his investigation into aligning LLMs. In this episode, he talks to Jon Krohn about the limitations of definitions for LLMs, training LLMs, and whether it is possible to train an LLM without alignment.Additional materials: www.superdatascience.com/784Interested in sponsoring a SuperDataScience Podcast episode? Visit passionfroot.me/superdatascien...

An episode of the Super Data Science: ML & AI Podcast with Jon Krohn podcast, hosted by Jon Krohn, titled "784: Aligning Large Language Models, with Sinan Ozdemir" was published on May 17, 2024 and runs 9 minutes.

May 17, 2024 ·9m · Super Data Science: ML & AI Podcast with Jon Krohn

Summary

Aligning LLMs: How can we teach pre-trained LLMs to hold a conversation and learn new information from each other? This was where Sinan Ozdemir began his investigation into aligning LLMs. In this episode, he talks to Jon Krohn about the limitations of definitions for LLMs, training LLMs, and whether it is possible to train an LLM without alignment.Additional materials: www.superdatascience.com/784Interested in sponsoring a SuperDataScience Podcast episode? Visit passionfroot.me/superdatascience for sponsorship information.

Episode Description