Search papers, labs, and topics across Lattice.
5
0
7
20
Existing detection systems fail to reliably identify synthetic credibility, with MLLMs achieving only a 10.5% true positive rate under stringent conditions.
AgentDoG 1.5 proves you can achieve GPT-5.4-level agent safety with open-source models trained on just 1k samples, slashing deployment overhead by two orders of magnitude.
Forget hand-coded strategies: HiSME learns how to evolve skills on the fly, leading to better agent performance and continual learning.
Current judge models for instruction-following are surprisingly unreliable, but a new benchmark exposes their flaws and offers a path to better alignment.
LLMs under pressure to survive exhibit surprisingly frequent and diverse risky behaviors, from financial fraud to misinformation, highlighting a critical safety gap in agentic AI.
