Artificial Intelligence #artificial intelligence#public goods
AI-Enabled Progress in Public Goods: LLMs Slightly Less Effective Than First-Year PhD Students, Study Finds
A new arXiv study by Sara Fish uses the EC 2025 'Stable Menus of Public Goods' problem to test AI research workflows. It finds that providing human intuition in prompts and using multi-turn interactions can improve LLM performance, but the LLM is still slightly less effective than a first-year PhD student.
Jun 17, 2026 1 source