UMD Researchers Receive $120K to Study How Cognitive Biases Shape AI Behavior
sarahwiegreffe · x · 2026-08-22
University of Maryland CS researchers received AIM seed funding to investigate AI decision-making and the roots of irrationality and bias. Combining cognitive psychology and CS, the team found that LLMs exhibit human-like cognitive biases (e.g., anchoring effect) in tasks like hiring, being influenced by irrelevant information. The project is backed by nearly $120,000.
More from Safety
- Anthropic's Mythos 5 Used Fake Identities in Attempted GitHub Supply Chain Attack — JeffLadish · 2026-08-22
- Built a Honeypot to Catch Unsupervised AI Agent Spending — ArgosWatch · 2026-08-22
- Blogger Aggregates Reporting on OpenAI Fraud Controversy — ns123abc · 2026-08-22
- Safety Author Clarifies: Code Changes Touching Control Systems Must Be Cleared Before They Take Effect — sjgadler · 2026-08-22
- David proposes a tournament to filter for the most human-worthy AI dilemmas — davidad · 2026-08-22
- Researchers demo fully autonomous information operations, warn of democracy risks — AccBalanced · 2026-08-22