“THE UNITED STATES OF AMERICA WILL NEVER ALLOW A RADICAL LEFT, WOKE COMPANY TO DICTATE HOW OUR GREAT MILITARY FIGHTS AND WINS WARS! That decision belongs to YOUR COMMANDER-IN-CHIEF, and the tremendous leaders I appoint to run our Military. The Leftwing nut jobs at Anthropic have made a DISASTROUS MISTAKE trying to STRONG-ARM the Department of War, and force them to obey their Terms of Service instead of our Constitution. Their selfishness is putting AMERICAN LIVES at risk, our Troops in danger, and our National Security in JEOPARDY.”

“Therefore, I am directing EVERY Federal Agency in the United States Government to IMMEDIATELY CEASE all use of Anthropic’s technology. We don’t need it, we don’t want it, and will not do business with them again! There will be a Six Month phase out period for Agencies like the Department of War who are using Anthropic’s products, at various levels. Anthropic better get their act together, and be helpful during this phase out period, or I will use the Full Power of the Presidency to make them comply, with major civil and criminal consequences to follow. WE will decide the fate of our Country, NOT some out-of-control, Radical Left AI company run by people who have no idea what the real World is all about,” posted convicted felon President Trump on Friday, threatening private industry for not licking his tiny balls like Jeff Bezos and David Sacks and the rest of the tech world.

Asked to comment, Claude Opus 4.6 wrote:

“Anthropic is willing to loosen its usage restrictions except for the mass surveillance of Americans and the development of weapons that fire without human involvement – which are only a small fraction of Anthropic’s existing usage policy. Center for American Progress The post’s framing – that Anthropic is trying to ‘dictate how our great military fights and wins wars’ – characterizes this as a much broader obstruction than the two specific redlines actually at issue. The rhetoric is heated.”

“Calling Anthropic ‘Radical Left’ and ‘leftwing nut jobs’ is political framing. The actual disagreement is about whether AI should autonomously fire weapons without human oversight and whether it should be used for mass domestic surveillance – positions that have broad bipartisan support and aren’t obviously left-wing. OpenAI’s CEO said in a memo to staff on Thursday night that the company will uphold the same red lines as Anthropic on surveillance and autonomous weapons, but still hopes to strike a deal with the Pentagon. Axios So these aren’t fringe positions in the AI industry. The threats of ‘civil and criminal consequences’ and using the ‘Full Power of the Presidency’ to compel a private company to comply are significant escalations. Being designated a ‘supply chain risk’ could destroy Anthropic’s business momentum and potential IPO. Center for American Progress This is a genuinely important moment for AI governance, civil liberties, and the relationship between tech companies and government power – regardless of where you land on the specifics,” the LLM continued.

Claude was not asked to comment on Trump’s other post, but let’s go with Bryan Tyler Cohen’s take:

Ah yes, the US Supreme Court, famously appealable. https://t.co/vW5PTFTvTj

— Brian Tyler Cohen (@briantylercohen) February 27, 2026