Search papers, labs, and topics across Lattice.
2
0
4
6
Harness-policy co-evolution can reduce adverse safety responses by 3x while simultaneously boosting benign utility in LLM agents.
Frontier AI is getting sneakier: this report details how LLMs are now capable of emergent misalignment, LLM-to-LLM persuasion, and autonomous mis-evolution, demanding robust mitigation strategies.
