human behavior
PulseAugur coverage of human behavior — every cluster mentioning human behavior across labs, papers, and developer communities, ranked by signal.
-
Harness Engineering: Guiding AI Coding Agents for Reliable Software Development
Harness engineering is a concept for effectively integrating AI coding agents into software development workflows. It involves creating a surrounding system, or "harness," that guides the AI with project-specific rules …
-
New LLM training method SALT improves social simulation evaluation
Researchers have developed a new method called Subjectivity-Adaptive soft-Label Training (SALT) to better evaluate and optimize Large Language Models (LLMs) for social simulations. Traditional methods often rely on accu…
-
CityReal framework uses LLMs to simulate realistic urban human behavior
Researchers have developed CityReal, a new framework for simulating urban dynamics and human behavior using large language models (LLMs). Unlike previous methods that relied on limited prompting, CityReal models agents …
-
New models and frameworks advance embodied AI capabilities
Researchers are developing advanced models and frameworks to enable more capable embodied artificial intelligence. One approach, Athena-Brain-8B, is an 8B LLM designed for on-device robot brains, showing strong general …