Official implementation of Maia-2, a unified human-like chess model across skill levels. For new projects, see Maia-3.
-
Updated
Jul 22, 2026 - Python
Official implementation of Maia-2, a unified human-like chess model across skill levels. For new projects, see Maia-3.
CLAUDE COWORK Governance templates for Claude Cowork — built from empirical research into long-horizon human-AI collaboration.
Quality Diversity through Human Feedback: Towards Open-Ended Diversity-Driven Optimization (ICML 2024)
Official implementation of "Adaptive Prompt Elicitation for Text-to-Image Generation" (ACM IUI 2026)
A Human-AI Alignment (HAA) framework for making human taste executable by AI coding agents.
Causal reasoning evaluation of LLMs with human benchmark
Replication package for How Coding Agents Fail Their Users: A Large-Scale Analysis of Developer-Agent Misalignment in 20,574 Real-World Sessions
Human-led AI evaluation research system for observing model behaviour through binary evals, signal traces, and retained failures.
Building Intelligent User Interfaces for Human-AI Alignment
Human Natural Structure (HNS) — Operating Structure for human cognition, behavior, and meaning generation
To associate your repository with the human-ai-alignment topic, visit your repo's landing page and select "manage topics."