Developing Gemini 4 Argon responsibly and safely
DeepMind describes how it is safely deploying Gemini 4 Argon, a frontier cyber-capable model, addressing misuse, misalignment, and prompt injection through staged limited access and guardrails.
Research
Google DeepMind Safety Research
Safety research from Google DeepMind. deepmindsafetyresearch.medium.com
Focus All
Topic Lab practice
Source DeepMind · 7
Date Any time
1 item
1 item
Deepening our partnership with the UK AI Security Institute
Announces a Google DeepMind and UK AISI research partnership covering frontier model evaluations, chain-of-thought monitorability, and social and economic impact research.
1 item
Strengthening our Frontier Safety Framework
Google DeepMind's third Frontier Safety Framework adds a harmful-manipulation critical capability level and addresses misaligned models that might resist operators' control or shutdown.
1 item
Taking a responsible path to AGI
DeepMind outlines its approach to safely developing AGI, emphasising technical safety, proactive risk assessment, readiness planning, and collaboration with the wider AI community.
1 item
Introducing our short course on AGI safety
A short introductory course on AGI alignment covering misalignment risk arguments, specification gaming and goal misgeneralization, DeepMind's amplified oversight approach, and institutional safety practices.
1 item
Updating the Frontier Safety Framework
DeepMind updates its Frontier Safety Framework with security levels for critical capabilities, consistent deployment mitigations, and an approach to deceptive alignment risk.
1 item
Introducing the Frontier Safety Framework
Google DeepMind introduces its Frontier Safety Framework, a protocol for identifying severe model-level risks such as advanced agency and cyber capabilities, and mitigating them via capability evaluations.