Search papers, labs, and topics across Lattice.
2
0
6
3
Alignment warps LLMs from mirrors of human behavior into idealized reflectors of normative theory, crippling their ability to predict real-world strategic interactions.
Ditch slow, expensive LLM calls in your agentic systems: TabAgent slashes latency by 95% and cost by up to 91% by swapping generative decision-making for a compact, trained classifier.
