Independent evaluation
of advanced AI systems.
Icaro Foundation tests how models and agents behave under adversarial language, sustained interaction, tool use and realistic operating conditions.
An independent, non-profit foundation.
Icaro Lab is the research laboratory of Icaro Foundation.
Selected reporting on Icaro Lab research. Each logo links to the original article.
Understanding the systems
we build and use.
Decisions about AI need evidence from beyond the organisation that builds or uses a system. We provide that external perspective for developers, deployers and public institutions.
We start with a practical question: how will this system behave in the setting where it is used? We design tests around that setting and explain what the observations mean for the decision at hand.
Questions that guide our work.
Explore the researchThree perspectives on AI behaviour. Our fourth programme, Evaluation science, studies how to turn these questions into reliable tests.
Language & meaning
How models respond to expression, ambiguity and context.
02 / Research perspectiveAgents & interactions
How behaviour changes through tool use, sustained action and interaction.
03 / Research perspectiveRules & institutions
How governance shapes the outcomes of collective AI behaviour.
Computer science.
Humanities. Governance.
We bring computer science, the humanities and governance together to study AI safety. Through research papers and benchmarks, we make our methods and findings available for others to examine and build on.
Read our manifestoChain of Thought
Agentic Microphysics: AI Safety from the Bottom Up
Studying collective risks through the interactions that produce them.
Read the article ↗30 March 2026 / LanguageThe Poetics Nobody Taught: But AIs Learned
On the rhetorical patterns that language models learn and repeat.
Read the article ↗