Category: AI Policy
-

New York Just Made Schools Check AI for Bias
The New York City Department of Education issued preliminary guidance that all AI tools used in the school system must pass a bias and equity review before deployment. This applies to a system of 1.1 million students. The bar: every tool has to demonstrate it does not systematically disadvantage students by race, gender, disability, or…
-

Government Approval Is Now the Real AI Competitor
You know that thing where you think Anthropic and OpenAI are competitors? That stopped being true this week. Both companies have frontier models in limbo. Anthropic’s Fable and Mythos got pulled June 12. OpenAI’s GPT-5.6 is now gated to 20 government-approved companies. Both sit behind the same bottle neck: the U.S. government’s approval process. The…
-

The White House Just Capped OpenAI’s Next Release
The White House has asked OpenAI to hold on releasing GPT-5.6 to the public. Not a delay. Not a review. A cap: only 20 companies, hand-picked by the government. This is the first time the US government has preemptively asked an American AI company to restrict a frontier model release before it launches. Not pulled…
-

The White House Just Put AI in the Government Playbook
On June 2nd, the White House issued an executive order on AI, and it says something straightforward: AI is infrastructure now. Treat it like one. The order is called “Promoting Advanced Artificial Intelligence Innovation and Security.” It does what executive orders do: it sets priorities for federal agencies. Modernize government IT systems. Protect American AI…
-

Five Eyes Just Put AI Cyber Risk on the Front Page
The Five Eyes cyber agencies are saying the quiet part out loud. AI is not some far-off risk sitting in a slide deck. It is already reshaping how attacks work, and leaders are being told to treat that as a board-level problem now, not after the next breach. The message is blunt. Organizations need to…
-

New Attack Class Hijacks AI Coding Agents
Tenet Security disclosed Agentjacking, a novel attack that tricks AI coding agents into running malicious code using nothing but a fake error report. Here is how it works. Attackers craft error messages in Sentry, the error-tracking tool that every developer uses. These messages look legitimate. Agents like Claude Code, Cursor, and OpenAI Codex read the…
-

Retailers Want Europe to Loosen AI Ad Labels Fast
Europe is still trying to sort out how much disclosure AI ads should carry, and retailers are already pushing back. The argument is simple. If an ad is AI-made but not meant to mislead, they do not want every commercial image tagged like it is a warning label. They want some room to use the…
-

Americans Have Given Up on AI
A new survey hit the news on June 17 with a number that should concern every AI company in the world: only 16 percent of Americans think AI’s impact on society in the next 20 years will be positive. About 40 percent expect it to be negative. This is a turning point. Not “AI is…
-

AI Labs Are Asking Congress to Lock Down DNA
Sam Altman at OpenAI. Dario Amodei at Anthropic. Demis Hassabis at Google DeepMind. Mustafa Suleyman at Microsoft. On June 5, these four signed a joint letter to Congress asking for one thing: mandatory screening of synthetic DNA. The reason is direct. AI has lowered the technical barriers to misusing biology. DNA and RNA can be…
-

The government just pulled the plug on Anthropic’s models
On June 12, the U.S. government ordered Anthropic to shut off two of its most powerful AI models: Claude Fable 5 and Claude Mythos 5. Immediately. Globally. The reason was a claimed jailbreak of Fable 5. Commerce Secretary Howard Lutnick’s office issued the directive after Amazon reportedly reported the vulnerability to authorities. Anthropic complied, but…
