Machine Psychology Insights
Thilo explores the fascinating realm of machine psychology, treating language models as participants in psychological experiments. He highlights the evolution of these models' cognitive abilities, particularly their performance on tasks like cognitive reflection tests. While pondering the future of artificial general intelligence, he notes the ongoing advancements in multimodal models that integrate language, images, and audio, suggesting we are on the brink of significant breakthroughs.In this clip
From this podcast
Data Skeptic
Emergent Deception in LLMs
Related Questions
Will large language models scale all the way to artificial general intelligence (AGI) as discussed in the episode AI Consciousness? Exploring the Possibility with Prof. Eric Schwitzgebel and the clip Mechanistic Interpretability?
Will large language models scale all the way to artificial general intelligence (AGI) as discussed in the episode Daniel Situnayake: AI on the Edge and the clip Perspectives on General Purpose AI, as well as in the episode Joscha Bach: Life, Intelligence, Consciousness, AI & the Future of Humans | Lex Fridman Podcast #392 and the clip Real-Time Learning?
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 LLMs and Agent Systems?