Experimental framework for cross-subtask malicious intent detection in stateless AI agents — research into open-weight model safety

21 Lessons, Get Started Building with Generative AI

This monorepo covers multiple QURI projects, including Squiggle language, Squiggle Hub and Metaforecast

Uncertainty and sensitivity analysis for GiveWell cost-effectiveness analysis

Squiggle programming language for intuitive probabilistic estimation features in Python

Search plugins for qBittorrent search feature

The development repository for LessWrong2 and the EA Forum, based on Vulcan JS

A Python library for integrating model-based and judgmental forecasting