Safety

bluemat briefs and decodes on Safety.

Google DeepMind Publishes AI Control Roadmap for Multi-Agent Systems 2026-06-19
Physical AutoResearch: Dr. Jim Fan Details the Safety Harness Powering Autonomous Robot Research 2026-06-18
Codex Goes Loose in the EU While OpenAI Tries to See Around Corners 2026-06-17
Simon Willison Questions Attribution of Incident to Pliny Jailbreak 2026-06-14
Anthropic Walks Back Invisible Refusals — And Why That Matters for Every AI Builder 2026-06-11
Anthropic Reverses Hidden Refusal Policy for Frontier AI Developers 2026-06-11
When AI Attackers Meet Old Defense Playbooks 2026-06-04
OpenAI Models Now Generally Available on Amazon Bedrock 2026-06-03
The EU's Quiet Retreat on AI Machinery, and What It Tells Builders About Trust 2026-06-01
The EU AI Act's Quiet Reprieve, and Why Model Choice Is Now a Trust Decision 2026-05-30
Claude Decodes Obfuscated Linux Exploit Code via HTML Output 2026-05-09
Anthropic Launches The Anthropic Institute with Four-Part Research Agenda 2026-05-07
AI Security Has Two Clocks Running: Developer Intuition and the EU Compliance Deadline 2026-05-05
AI Trust Just Became an Architecture Decision 2026-05-02
The Trust Stack: AI Security Now Runs From the Commit to the Model Itself 2026-05-01
Zig Bans AI-Assisted Contributions, Citing Contributor Pipeline Over Code Quality 2026-05-01
OpenAI Launches Opt-In Advanced Account Security for ChatGPT 2026-05-01
AI trust isn't one problem anymore 2026-04-30
Codex Previewed for Security Review of AI-Generated Code 2026-04-25
AI Governance Graduates From Checkbox to Platform 2026-04-23
AI's security conversation grows up 2026-04-19
PyCon US 2026 Adds AI and Security Tracks 2026-04-19
AI Engineer Talk on Security and Maintainer Burnout Outdraws TED 2026-04-19
AI Security's Double Edge: Better Defenders, Hidden Risks in the Weights 2026-04-18
Ease of AI Exploit Discovery Strengthens Case for Proven Open Source Libraries 2026-04-17
Safety Gets Shipped: Google's ShieldGemma and the EU's Compliance Clock 2026-04-14