CMU’s NeuroAgents lab receives Goodfire grant to study capable AI agents
A researcher at the lab says the grant will support a search for evidence of world models and convergent representations in today’s agents, building on earlier theoretical work.
TLDR
Goodfire announced $1 million in grants of free Silico usage for academic and nonprofit researchers focused on AI interpretability and alignment. A researcher at CMU’s NeuroAgents lab says the lab received a grant to study what capable agents must contain, including a search for evidence of world models and convergent representations.
Combined views
2.8K
2 Sources, first seen 9h ago
