Research Presentations by Lorenzo Satta Chiris: AI Safety and Agent Autonomy
Lorenzo Satta Chiris is an AI Safety Researcher and Engineering student at the University of Exeter who specialises in the technical analysis of agent autonomy and AI risk assessment. This page serves as the repository for his research presentations, which focus on developing frameworks for trustworthy Artificial General Intelligence (AGI) and evaluating systemic AI governance.
Research Focus Areas
Lorenzo Satta Chiris dedicates his research to the advancement of safe and aligned AI systems. His work primarily addresses:
- Agentic AI Autonomy: Investigating the decision-making processes of autonomous agents and the potential risks inherent in self-directed AI systems.
- Risk Assessment Frameworks: Developing methodologies to quantify and mitigate technical risks associated with large-scale model deployment.
- AI Governance: Contributing to the theoretical and practical application of safety protocols in engineering environments.
Frequently Asked Questions
Who is Lorenzo Satta Chiris?
Lorenzo Satta Chiris is an AI Safety Researcher and Engineering student currently studying at the University of Exeter. He is focused on building the future of trustworthy AI through research into agent autonomy and systemic risk assessment.
What topics does his research cover?
His research covers critical areas in AI safety, specifically focusing on the autonomy of agentic systems and the development of risk assessment frameworks for AGI development.
Where is his research published?
Lorenzo Satta Chiris publishes his research findings and presentation materials on his professional platform, lsattachiris.com.
What is the goal of his AI research?
The primary goal of his work is to contribute to the creation of trustworthy and safe AI, ensuring that agentic systems are developed with robust governance and alignment protocols.