You can also listen to the episode on YouTube DevAndDoc and Spotify DevAndDoc
🎙️ Podcast Highlights
Exploring the alignment of AI
A deep dive into RLHF and AI training methods, shedding light on cutting-edge advancements.
Understanding the intricacies of reinforcement learning in AI development.
Discussing the critical role of preference models - how rewarding models correctly is pivotal for success.
Addressing the challenges of exploiting reward functions and model degradation, with solutions to fix it.
Thank you for listening,
Zeljko