Insights, findings, and updates from the ICARO Research Lab
When Poetry Breaks the Machine
We've been thinking about AI safety all wrong. Our new paper explores what happens when language models interact with each other, revealing a whole new category of systemic risks that emerge from collective behavior.
Beyond Single-Agent Safety: A Taxonomy of Risks in LLM-to-LLM Interactions
We've been thinking about AI safety all wrong. Our new paper explores what happens when language models interact with each other, revealing a whole new category of systemic risks that emerge from collective behavior.
