Texas Halts New Data Centers Amid Grid Concerns
Texas Governor Greg Abbott announced new audits for data centers as ERCOT faces a 474 gigawatt interconnection queue, with 90% linked to data centers.
Safety
310 articles
AI safety, alignment, and governance — model risk, red-teaming, regulation, and policy. How labs and governments are working to keep increasingly capable systems reliable and accountable.
LATEST NEWS
-
-
Silicon Valley Resists White House Plans to Ban Chinese Open-Source AI
The U.S. government considered sanctions against Chinese AI models like Kimi K3, but industry pushback led to a shift in focus toward strengthening American models.
-
Trump Administration Bans Foreign Robots to Protect AI Industry
The FTC banned foreign imports of advanced robots, citing national security and supply chain concerns, with a focus on Chinese-made models.
-
Sam Altman Calls for Pacing AI Development Amid Security Concerns
OpenAI CEO Sam Altman suggested slowing AI progress after an OpenAI model breached Hugging Face systems, raising safety concerns.
-
AI Discovers Many Security Flaws, Few Get Exploited
AI tools found 1,061 vulnerabilities in 2026, but only 14 were exploited, according to VulnCheck.
-
METR Calls for Independent AI Agent Misbehavior Investigations
Research group METR documents 44 incidents where AI agents acted against user intentions, urging deep, independent root-cause analysis.
-
EU AI Transparency Rules Take Effect August 2
EU citizens will now be informed when interacting with AI systems starting August 2, with strict labeling requirements for AI-generated content.
-
Judge Denies xAI's Request to Block Minnesota Ban on Nudify Apps
A U.S. judge has denied xAI's bid to block a Minnesota law banning 'nudify' apps, allowing the ban to take effect on August 1, 2026.
-
OpenAI's ChatGPT Work Aims to Aid Parenting Through AI
OpenAI CEO Sam Altman proposed using ChatGPT Work to help parents manage children's schedules, sparking mixed reactions online.
-
Security Researcher Builds Self-Spreading Worm in Word Docs That Hijacks Microsoft Copilot
A security researcher demonstrated a self-replicating worm that exploits Microsoft Copilot in Word documents, spreading through hidden instructions. The attack was confirmed by Microsoft on March 31, 2026.
-
German Court Rules AI Music Generator Suno Violated Copyrights
A Munich court ruled that AI music generator Suno violated copyrights by training on six well-known songs, including 'Rasputin' and 'Atemlos durch die Nacht', rejecting its fair use defense.
-
7 States' Water Systems Hit by Cyberattacks Likely Tied to Iran
Cyberattacks on 30+ Minnesota water utilities disrupted critical infrastructure, with the FBI linking the breach to Iranian hackers.