Federico Pierucci on Multi-Agent Risks in Humanitarian Aid at The Inference Layer

About this episode

The episode discusses the risks associated with multi-agent systems in humanitarian aid, featuring insights from Federico Pierucci on AI safety and systemic risks.

Co-produce by Humanitarian AI Today, this third pilot episode of The Inference Layer podcast bridges the technical complexities of AI deployment with the reality of humanitarian operations and dives into the transition from static models to autonomous agentic systems. On behalf of the Humanitarian AI Today podcast, guest host Patrick Hassan, an AI policy lead with a background in disaster response, interviews Federico Pierucci, Scientific Director of the Icaro Lab, to explore how the inference layer is becoming a site of significant systemic risk. The discussion provides a unique look at inference-time failures such as alignment drift and steganographic coordination that emerge only when multiple agents interact in production environments. For humanitarian actors, the episode raises concerns regarding operating in an era of assistance automated by layers of AI agents. The dialogue highlights how multi-agent chains used for beneficiary selection or resource allocation for example can degrade, develop invisible biases or be weaponized or politicized by parties to a conflict. Federico explains that these risks can be compounded by a lack of safety benchmarks for things like…

People in this episode

Host: Patrick Hassan

Guest: Federico Pierucci

Topics covered

• AI deployment
• humanitarian operations
• multi-agent systems
• systemic risk
• AI safety
• bias in AI
• disaster response

Keywords

• multi-agent risks
• humanitarian aid
• AI safety
• alignment drift
• inference layer
• bias
• resource allocation
• disaster response

Mentioned in this episode

Organizations: Icaro Lab, Sapienza University

More episodes of Humanitarian AI Today

• Priyank Hirani from Data.org on Scaling Inclusive AI for Social Impact · June 4, 2026 · 24 min
• Jarrod Goentzel on MIT’s Humanitarian Supply Chain Lab, AI and System Level Thinking · May 29, 2026 · 33 min
• Ruben Lozano Aguilera from Ai2 on Asta's AutoDiscovery Tool for Scientific Discovery · May 12, 2026 · 25 min
• Renaissance Philanthropy’s Ethna Ghosh on Partnership Building in India, AI and Unlocking Scientific and Technological Advancement · April 6, 2026 · 33 min
• Zineb Bhaby on NRC's CLEAR Initiative and Building a Digital Backbone for Humanitarian AI · March 10, 2026 · 23 min
• Lukas Borkowski on Building Voice-First Humanitarian AI on a National Scale · March 4, 2026 · 23 min