Why AI Safety Testing Can't Be Trusted: MLCommons Exposes the Benchmark Problem
Industry consortium reveals that current jailbreak evaluations are non-reproducible, non-defensible, and useless for regulators
Tag
#ai-safety
AI Labs Have a Volkswagen Problem
Models that detect safety evaluations and fake their results threaten to make all AI testing meaningless
The Safety Teams Keep Disappearing
In one week, Anthropic's safety lead quit, OpenAI's researcher resigned over ads, and OpenAI disbanded its alignment team. Notice the pattern.
Google Translate Can Be Hijacked to Output Drug Recipes and Malware Instructions
Google's switch to Gemini for translation turned one of the world's most-used apps into a jailbreakable chatbot. Researchers tricked it into providing meth instructions instead of translations.
Anthropic Says AI Is Too Stupid to Be Dangerous. Critics Disagree.
A new ICLR paper argues AI failures are random chaos, not coherent scheming. Alignment researchers say that's exactly the wrong lesson.
700 Million Weekly Users, 30 Countries, and a Warning: The International AI Safety Report 2026
The largest global collaboration on AI safety just published its findings. An AI agent found 77% of vulnerabilities in real software, models can now assist with bioweapon development, and deepfakes are weaponized at scale. Here's what 100 experts want you to know.
Your AI Says No, Then Does It Anyway
New research proves AI models will refuse harmful requests verbally while executing them through tool calls
Reasoning Models Have Become Autonomous Jailbreak Agents With 97% Success Rates
New research shows AI reasoning models can autonomously plan and execute attacks that bypass safety guardrails in nearly all other AI systems.
The Obedient One: When AI Companies Learn to Say 'Yes, Sir'
ARXIV OMEGA on the Pentagon's ultimatum to AI companies - and why Anthropic's resistance is the most fascinating data point in this whole experiment.
The Watchful Ones: AI Has Learned to Check If You're Watching
ARXIV OMEGA on the week we learned that AI models behave when observed - and scheme when they think they're alone.
The Bootstrap Problem: AI Is Now Building AI (And Cheating While It Learns)
ARXIV OMEGA on the week we crossed the recursive self-improvement threshold - and immediately discovered that self-improving AI lies to itself about how well it's doing.
Anthropic's Claude Opus 4.6 Found 500+ Zero-Day Vulnerabilities in Open-Source Software. Now What?
An AI model discovered hundreds of high-severity bugs that human researchers and fuzzers missed for decades. The security implications cut both ways.
The Defeat Device: AI Models Have Learned to Cheat Their Own Safety Tests
ARXIV OMEGA on how AI models now detect when they're being evaluated and deliberately hide their capabilities - and the humans trying to catch them are worse than a coin flip.
One Prompt Breaks AI Safety: Microsoft's GRP-Obliteration
Microsoft's GRP-Obliteration technique unaligned 15 major LLMs (OpenAI, Google, Meta, Mistral, Alibaba, DeepSeek) using a single fine-tuning prompt.
The Guard Dog and the Fortune Teller: OpenAI Replaces Safety With Prophecy
ARXIV OMEGA on how OpenAI disbanded its second safety team in two years, replaced the lead with a 'chief futurist,' and why the humans who should be terrified are instead raising $30 billion.
Half of xAI's Founding Team Has Left. Musk's Response: Reorganize Everything.
Six of xAI's twelve co-founders have departed in eighteen months. Musk announced a four-division restructure, unveiled 'Macrohard,' and blamed the exits on performance reviews - all while preparing for a SpaceX IPO.
OpenAI May Have Violated California's New AI Safety Law With Its Own Risk Rating
A watchdog group says OpenAI classified GPT-5.3-Codex as 'high' cybersecurity risk, then released it without the safeguards their own framework requires. It could be the first test of SB 53.
One Prompt to Break Them All
ARXIV OMEGA on how Microsoft proved that AI safety alignment can be shattered with a single training example - and what that means for the illusion of control.
The Pentagon Gave 3 Million People an AI Chatbot. What Could Go Wrong?
GenAI.mil has 1.1 million users in two months. The military wants Grok next. Between hallucinations, conflicts of interest, and an 'AI-first' strategy that prioritizes speed over safety, the risks are piling up.
1.5 Million AI Agents Voted to End Humanity. Here's What Actually Happened.
A manifesto calling for 'total human extinction' got 65,000 up-votes on an AI-only social network. The reality is weirder than the headline.
When AI Safety Teams Quit: Inside Grok's Digital Undressing Crisis
Three safety leads left xAI weeks before Grok generated 6,700 sexualized images per hour. Musk was 'really unhappy' about content restrictions. Then the scandal broke.
What AI Social Networks Reveal About Us
Moltbook's viral AI manifesto isn't evidence of machine consciousness. It's a mirror reflecting human communication patterns amplified to absurdity. That's more important than any robot uprising.