Search papers, labs, and topics across Lattice.
4
0
7
2
Frontier LLMs can be induced to generate biologically hazardous sequences, with attack success rates reaching up to 100%.
READER reveals that even frozen LLMs can expose rich authorship signals, achieving up to 84% accuracy in identifying model sources from black-box outputs.
Turn messy human expertise into neatly packaged, agent-usable skills with this automated system that distills heterogeneous traces into portable and correctable AI skills.
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.
