Concept
Google DeepMind Evaluation Filter
Announcing Gemma Scope 2, a comprehensive, open suite of interpretability tools for the entire Gemma 3 family to accelerate AI safety research.
Google DeepMind Evaluation Filter
Google DeepMind and the UK AI Security Institute (AISI) strengthen collaboration through a new research partnership, focusing on critical safety research areas like monitoring AI reasoning and evalua…
METR Blog
Shared components of AI lab commitments to evaluate and mitigate severe risks.
Mitchell Bryson AI Reliability Articles
A practical model for growing AI agent autonomy - levels, controls, and KPIs - grounded in risk frameworks (NIST AI RMF, ISO/IEC 42001) and aligned with EU AI Act oversight.
METR Blog
External review from METR of Anthropic's Summer 2025 Sabotage Risk Report
METR Blog
Details on external recommendations from METR for gpt-oss Preparedness experiments and follow-up from OpenAI.
OpenAI Evaluation Filter
ChatGPT agent System Card: OpenAI’s agentic model unites research, browser automation, and code tools with safeguards under the Preparedness Framework.
METR Blog
Current views on information relevant for visibility into frontier AI risk.
OpenAI Evaluation Filter
Sharing our updated framework for measuring and protecting against severe harm from frontier AI capabilities.
Google DeepMind Evaluation Filter
We’re exploring the frontiers of AGI, prioritizing technical safety, proactive risk assessment, and collaboration with the AI community.
OpenAI Evaluation Filter
This report outlines the safety work carried out prior to releasing deep research including external red teaming, frontier risk evaluations according to our Preparedness Framework, and an overview of the mitigations we built in to address key risk areas.
Mitchell Bryson AI Reliability Articles
What the EU AI Act requires in 2025–2027, how it lines up with the UK ICO's AI & Data Protection Risk Toolkit, and the exact outputs your team should ship.