Search papers, labs, and topics across Lattice.
7
3
9
11
Environment evolution can reveal 17% more safety failures in complex tasks compared to static benchmarks, reshaping our understanding of agent vulnerabilities.
Short-session tests miss critical developmental risks in AI companions, with stable evaluations only emerging after 140 interaction turns.
Current AI agents are alarmingly effective at packaging pseudoscience in credible scientific language, with refusal rates near zero.
SentGuard detects 90.5% of unsafe content within two sentences, revolutionizing real-time moderation for large language models.
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.
LLMs exhibit a surprising degree of moral indifference, compressing distinct moral concepts into uniform probability distributions, a problem that persists across model scales, architectures, and alignment techniques.
Even state-of-the-art multimodal LLMs like GPT-5.2 and Claude 4.5 can be jailbroken nearly half the time using OpenRT's diverse suite of attacks, revealing a critical lack of generalization across attack paradigms.
