🛟 AI Safety - mmasnick · Scour

AI Agents Are Creating a New Cybersecurity Blind Spot 🤖Agentic AI

blog.itsecurityexpert.co.uk·6d·Blogger

Safety-Constrained Reinforcement Learning with Post-Training Reachability Verification for Robot Navigation 🤖Agentic AI

The hard core of alignment (is robustifying RL) 🔐Encryption Policy

lesswrong.com·2d

https://www.together.ai/blog/safety-models 🤖AI

together.ai·4d

Existing Policy Proposals Targeting Present and Future Harms 🔐Encryption Policy

Institutional Control Architecture: A Standard for Autonomous AI Governance 🤖Agentic AI

ica-manual.netlify.app·5d·Hacker News

How AI is De-Risking Drug Development and Companion Diagnostics 🤖Agentic AI

3quarksdaily.com·5d

Top AI Risks Every Security Team Should Be Testing For 🤖AI

Governance for AI Agents with Data Developer Platforms 🤖Agentic AI

mlops.community·4d

AI is an accelerator, not a shortcut, when tackling legacy systems 🤖Agentic AI

madetech.com·5d

Two Fronts, One Risk: Securing Yesterday’s Debt and Today’s AI Code 🤖Agentic AI

malware.news·5d

LiSA: Lifelong Safety Adaptation via Conservative Policy Induction 🤖Agentic AI

The hidden risk of non-human identities in AI adoption 🤖Agentic AI

helpnetsecurity.com·4d

Cybersecurity and AI: The Evolving Security Landscape 🔐Encryption Policy

Navigating the rise of agentic AI in 2026 🤖Agentic AI

·6d

The Architecture of Immanent AI: From Superficial Censorship to Ethics as an Energetic State of… 🤖Agentic AI

·4d

How enterprises can safely scale agentic AI 🤖Agentic AI

·5d

Import AI 456: RSI and economic growth; radical optionality for AI regulation; and a neural computer 🤖Agentic AI

importai.substack.com·6d·Substack

CMU Researchers Develop AI System to Help Prevent Airport Collisions 🤖Agentic AI

Artificial Intelligence and the New Frontier of Global Diplomacy 🤖Agentic AI

moderndiplomacy.eu·4d

Sign up or log in to see more results

Log in to enable infinite scrolling