Topic
Llms
Recent coverage of Llms from across the web.
-
Zscaler finds autonomous agents succumb to IPI traps -
Free-text answers and LLMs reveal hidden reasons behind human choices -
Chinese LLMs Broaden the Gap Between Attackers & Defenders -
As buyers make decisions through LLMs, Bobcat's Laura Ness Owens is focusing more on customer experience
-
The Download: a startup has a solution for AI’s groupthink problem - LLMs are stuck in a groupthink groove. This startup is trying to get them out.
-
Security researchers tricked LLMs into giving them cocaine recipes by abusing role models for prompt injection
-
Prompt injection is exploiting enterprise AI's biggest design flaws by targeting agents, RAG pipelines and model routers