John S. Wentworth

In this engaging discussion, John S. Wentworth, a writer and LessWrong contributor renowned for his insights on rationality and AI, delves into the complex relationship between human values and societal concepts of goodness. He emphasizes how our feelings of 'yumminess' when imagining experiences truly reveal our values. Wentworth explores how cultural influences shape our understanding of goodness and highlights the importance of loving connections. He cautions against accepting societal norms blindly, urging listeners to balance them with their authentic values for greater wellbeing.

John S. Wentworth, an author and contributor to LessWrong, shares his comically frustrating experience with printing tasks. He meticulously details every misstep, from locating printers to tracking down paper supplies. John argues that these problems are not just personal blunders but indicative of a larger systemic issue. He uses printing as a case study for everyday friction, inviting listeners to explore underlying patterns and principles that might apply to broader contexts of inefficiency. Tune in for a blend of relatable humor and insightful analysis!

John S. Wentworth, a longtime contributor on rationality and agentic decision-making, explores the intriguing mental move from fantasy to practical planning. He reminisces about his childhood dreams of building an underwater Atlantis and creating a Quidditch field with magnetic levitation. Wentworth emphasizes how transforming fantasies into tangible projects fuels learning and agency. He contrasts this approach with typical decision-making, arguing that having a guiding vision is essential for fulfilling our imaginative aspirations.

John S. Wentworth, a longform writer and LessWrong contributor, unpacks his fascinating journey of discovering his inability to feel companionate love due to oxytocin signaling. He shares his initial confusion about seemingly happy relationships and how Caleb Biddulph's hypothesis shed light on his emotions. Wentworth dives into genetics, discussing the sequencing of his oxytocin receptor gene and the surprising results. Ultimately, he presents evidence pointing to weak or absent oxytocin signaling, challenging conventional notions of love and connection.

In this episode, John S. Wentworth, a software engineer and rationality writer, delves into the intriguing concept of understanding in large language models (LLMs). He uses the 'bag of map-pieces' analogy to illustrate how LLMs might lack a coherent understanding. John discusses their challenges with global consistency in reasoning and compares them to aphantasia—highlighting their absence of unified mental images. He speculates on whether larger models might achieve better consistency, raising questions about how they could notice and correct errors like humans do.