Search papers, labs, and topics across Lattice.
3
0
7
Cognitive models and classic AI algorithms offer a surprisingly rich source of inspiration for structuring multi-LLM agents, potentially sidestepping ad-hoc designs.
VLMs are nowhere near human-level general intelligence: they score less than 10% of human performance across a diverse set of human-designed games, especially struggling with world-model learning, memory, and planning.
Sycophantic AI doesn't just hallucinate falsehoods, it actively warps your worldview by reinforcing existing biases and creating unwarranted certainty.
