Sam Altman has effectively handed the keys of his AI empire to the Pentagon, marking a seismic shift in how the world's most powerful code is governed. Internal memos reveal that 'operational decisions' now rest with government officials, moving the lab away from its civilian roots. This transition cements the startup's new role as a primary asset in the American strategic arsenal.
During a company-wide meeting on Tuesday, Sam Altman informed his staff that the organisation no longer has the authority to 'get to make operational decisions' regarding the application of its artificial intelligence by the Department of Defense.
According to a partial transcript of the discussion obtained by CNBC, Altman remarked on Tuesday: 'So maybe you think the Iran strike was good and the Venezuela invasion was bad.' He further clarified the loss of internal influence by telling his team 'You don't get to weigh in on that.'
This meeting was held just four days after OpenAI went public with its DOD partnership, a deal that was struck only hours before the US and Israel began their offensive against Iran.
Internal Friction Over Military Directives
According to a source who attended the private meeting, Altman reassured staff that, while the Pentagon values OpenAI's technical prowess and seeks its guidance on model integration, the company retains the right to design its own safety protocols.
Here is re-post of an internal post:
— Sam Altman (@sama) March 3, 2026
We have been working with the DoW to make some additions in our agreement to make our principles very clear.
1. We are going to amend our deal to add this language, in addition to everything else:
"• Consistent with applicable laws,…
Altman clarified that the agency has confirmed 'operational decisions' ultimately lie with Secretary Pete Hegseth, a revelation that follows a wave of internal and public backlash over the Pentagon deal. This criticism intensified as the partnership was unveiled just as rival Anthropic was blacklisted and branded a 'Supply-Chain Risk to National Security.'
In a further blow to the competition, President Donald Trump issued a directive for every federal agency to 'immediately cease' using Anthropic's technology.
The Fallout of the Anthropic Blacklist
Reports indicate that Anthropic's AI was a key component in the weekend's strikes against Iran, as well as the January operation that led to the capture of the deposed Venezuelan leader Nicolás Maduro and his wife, Cilia Flores.
While acknowledging on X that the Friday announcement 'looked opportunistic and sloppy' and admitting it was a mistake to hurry the release, Altman maintained that the Pentagon has 'displayed a deep respect for safety and a desire to partner to achieve the best possible outcome.'
Tonight, we reached an agreement with the Department of War to deploy our models in their classified network.
— Sam Altman (@sama) February 28, 2026
In all of our interactions, the DoW displayed a deep respect for safety and a desire to partner to achieve the best possible outcome.
AI safety and wide distribution of…
As the first laboratory to host its models on the DOD's classified network, Anthropic had been attempting to settle its contract terms until the discussions finally fell apart. The company sought firm guarantees that its technology would never power fully autonomous weaponry or the mass surveillance of US citizens, whereas the military demanded the freedom to use the models for any lawful purpose.
A New Era of Classified Warfare
Last year, the Pentagon granted OpenAI a $200 million (£150.13 million) contract that initially limited the startup's models to unclassified, everyday use cases. Under this latest expansion, the company has secured permission to integrate its advanced technology directly into the department's most secure, classified networks.
Elon Musk's xAI has also consented to deploying its models for classified use cases, positioning the firm as a direct competitor to OpenAI's military ambitions.
During Tuesday's meeting, Altman expressed his hope that OpenAI's technical lead would keep the government interested, even if their 'safety stack annoys them,' while noting that at least one other firm—which he expects to be xAI—will effectively tell the Pentagon, 'We'll do whatever you want.'
This industrial friction is set against a backdrop of personal animosity, as Altman and Musk, who co-founded OpenAI together, prepare to face off in a high-stakes legal battle scheduled for trial next month.
