Ep 64: GPT 4.1 Lead at OpenAI Michelle Pokrass: RFT Launch, How OpenAI Improves Its Models & the State of AI Agents Today
Unsupervised Learning
00:00
Advancements in Multimodal AI and Fine-Tuning Techniques
This chapter explores the latest advancements in multimodal AI models, particularly version 4.1, and the renewed importance of fine-tuning methods. It highlights the efficacy of reinforcement learning from human feedback (RFT) compared to supervised fine-tuning (SFT) and offers insights into task-specific model selection. The discussion also delves into the intricacies of model selection and the challenges in AI deployment, particularly in sensitive applications like tax preparation.
Transcript
Play full episode
