Evolution of AI Alignment
Connor discusses the shift in mainstream AI alignment research towards neural networks and GPU-based models. Miri's approach challenges traditional views, aiming to define intelligence and optimization processes for future super intelligent systems. The conversation delves into the pre-Newtonian stage of intelligence research and the quest for fundamental understanding in decision theory.In this clip
From this podcast
Machine Learning Street Talk (MLST)
AI Alignment & AGI Fire Alarm - Connor Leahy
Related Questions
Can we predict AI capabilities as discussed in the episode 168 - How to Solve AI Alignment with Paul Christiano and the clip Understanding AI Generalization?
What do you think about the potential for Large Language Models (LLMs) to scale to Artificial General Intelligence (AGI) as discussed in the episode Francois Chollet - ARC reflections - NeurIPS 2024 and the clip Future of Programming?
Will large language models scale all the way to artificial general intelligence (AGI) as discussed in the episode Gary Marcus' keynote at AGI-24 and the clip Generalization Challenges? Additionally, what are the insights from the episode MEGATHREAT: The Dangers Of AI Are WEIRDER Than You Think! | Yoshua Bengio and the clip Neural Networks Explained?