🎯 Rationalism - sfafaf3q2 · Scour

NARE – A framework that "crystallizes" LLM reasoning into fast Python scripts 💬Philosophy of Language

github.com·4d·Hacker News, Hacker News

AI Models Excel in Doctors' Clinical Reasoning Tasks 🧠Working Memory

miragenews.com·11h

Designing with AI without losing your mind (8 minute read) 💭Cognitive Load

·4d

LaDiR: Latent Diffusion Enhances LLMs for Text Reasoning 💬Philosophy of Language

machinelearning.apple.com·1d·Hacker News

Latent reasoning models might be a good thing? 🧠Cognitive Biases

lesswrong.com·2d

Participation and Immersive Imagination in Thought Experiments 🌆Speculative Urbanism

philsci-archive.pitt.edu·6d

AGI is Probably Inevitable: A Model of Societal Ruptures 📉Degrowth

lesswrong.com·1d

LLM Style Slop is Absolutely Everywhere 💬Speech Act Theory

lesswrong.com·2d

Scaffolding vs Reinforcement Finetuning for AI Forecasting 🧠Rationality

lesswrong.com·1d

Roko's basilisk may work on humans 🧠Rationality

lesswrong.com·4d

Communicating with people who disagree on "obvious" things 🧠Cognitive Biases

lesswrong.com·6d

"Bad faith" means intentionally misrepresenting your beliefs 🔍Epistemology

lesswrong.com·4d

An Empirical Study of Methods for SFTing Opaque Reasoning Models 🧠Cognitive Biases

lesswrong.com·6d

Can you build a public debate platform that rewards argument quality over tribal affiliation? I've been trying to. 💬Philosophy of Language

lesswrong.com·4d

Retrospective on my unsupervised elicitation challenge 💬Philosophy of Language

lesswrong.com·4d

Spontaneous introspection in conversation tampering 💬Speech Act Theory

lesswrong.com·4d

How does Reinforcement Learning Affect Models 📊Behavioral Economics

lesswrong.com·3d

LessWrong Shows You Social Signals Before the Comment 🌐Internet Culture

lesswrong.com·3d

Alignment Faking Replication and Chain-of-Thought Monitoring Extensions 📓Note-Taking

lesswrong.com·4d

Ballistic FOMO 🧠认知科学

lesswrong.com·6d

Log in to enable infinite scrolling