Search papers, labs, and topics across Lattice.
2
0
4
2
Frontier LLMs can be induced to generate biologically hazardous sequences, with attack success rates reaching up to 100%.
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.
