Research

Our research

Our research explores the technical, political, and institutional challenges of building safer AI systems. We aim to inform policy, support practitioners, and contribute to a growing body of knowledge that bridges theory and real-world impact.

featured
  • 02.08.2026
  • Technical Report
GLM-5.2 Risk Evaluation Report
Chinmayi Dixit*, Jacob Davies*, Jasmine Li, Ben Snodin, Jack Kengott, Henry Papadatos
SaferAI's independent evaluation of GLM-5.2, the first in Europe, tests Zhipu AI's open-weight flagship across the four systemic risk areas in the EU Code of Practice and finds frontier-level capability on cyber and biology benchmarks without the safeguards frontier developers apply.
read more
  • 16.07.2026
  • Paper
Lessons from External Review of DeepMind’s Scheming Inability Safety Case
Stephen Barrett, Francisco Javier Campos Zabala, Sean P. Fillingham, Umair Siddique, James Walpole, Robin Bloomfield, Henry Papadatos
An independent, Assurance 2.0-based review of Google DeepMind's public safety case for Gemini 2.5 Pro finds gaps that materially affect what the case can support, and sets out concrete recommendations for how external review of frontier AI safety cases should be done.
read more
  • 16.07.2026
  • Paper
Exploring Systems-Thinking Approaches to Loss of Control Risk
Aurelio Carlucci, Sean P. Fillingham, James Walpole, Jakub Kryś
read more
  • 24.03.2026
  • Memo
The Case for European Investment in High-Risk, High-Reward AI Reliability Research
Chloé Touzet, Lily Stelling, Bruno Galizzi
read more
  • 10.12.2025
  • Technical Report
Toward Quantitative Modeling of Cybersecurity Risks Due to AI Misuse
Steve Barrett, Malcolm Murray, Otter Quarks, Matthew Smith, Jakub Kryś, Siméon Campos, Alejandro Tlaie Boria, Chloé Touzet, Sevan Hayrapet, Fred Heiding, Omer Nevo, Adam Swanda, Jair Aguirre, Asher Brass Gershovich, Eric Clay, Ryan Fetterman, Mario Fritz, Marc Juarez, Vasilios Mavroudis, Henry Papadatos
read more
Recent
type
  • Technical Report
  • Memo
  • Paper
subject