Yahoo Finance

Trump Administration Asks OpenAI to Stagger Release of AI Model

CNBC

OpenAI limits new AI models to 'trusted partners' at request of U.S. government

R street

The United States Must Reject Government Control of Artificial Intelligence

Assessing Trumps Executive Order on AI Oversight

The Hill

Trump’s last-minute AI order switch exposes White House divides

AdamThierer

arXiv.org

[2307.03718] Frontier AI Regulation: Managing Emerging Risks to Public Safety

MS Now

Trumps executive order on AI is insidious

TechCrunch

The White House is asking OpenAI to slow roll the release of its new model over safety concerns

The Associated Press

OpenAI limits its latest ChatGPT product to Trump-approved customers during cybersecurity review

Guardian

OpenAI staggers AI model release after Trump administration request

Axios

Trump administration asks OpenAI to limit next model release over security concerns

Financial Times

Trump administration asks OpenAI to stagger release of new model to vet users

White House asks OpenAI to limit its next model release

The Washington Post

U.S. government will decide who gets to use latest upgrade to ChatGPT

Politico

Trump administration steps in to limit OpenAI’s latest model launch

Slashdot

Trump Administration Asks OpenAI To Stagger Release of New Model

Bloomberglaw

Trump Administration Asks Openai To Stagger Release Of Ai Model

Trump administration asks OpenAI to stagger release of new model, The Information reports

Metaculus

Cybersecurity Laws for Powerful AI by 2030?

OpenAI announced Friday that its newest AI system, GPT-5.6 Sol, would be released only to a small group of government-approved partners, following a request from the Trump administration to limit the rollout amid concerns over the system's advanced cybersecurity capabilities.

OpenAI announced Friday that its newest AI system, GPT-5.6 Sol, would be released only to a small group of government-approved partners, following a request from the Trump administration to limit the rollout amid concerns over the system's advanced cybersecurity capabilities.

The staggered release was requested by the White House's Office of the National Cyber Director and Office of Science and Technology Policy. Commerce Secretary Howard Lutnick also spoke with OpenAI CEO Sam Altman on Wednesday, seeking assurances that all relevant agencies had tested and approved the system.

The staggered release was requested by the White House's Office of the National Cyber Director and Office of Science and Technology Policy. Commerce Secretary Howard Lutnick also spoke with OpenAI CEO Sam Altman on Wednesday, seeking assurances that all relevant agencies had tested and approved the system.

OpenAI said Sol is its most capable system to date, with improvements in coding, biology and cybersecurity. The company said the system is better at helping users identify and fix vulnerabilities than at carrying out attacks, and does not cross its own "critical" cybersecurity risk threshold.

OpenAI said Sol is its most capable system to date, with improvements in coding, biology and cybersecurity. The company said the system is better at helping users identify and fix vulnerabilities than at carrying out attacks, and does not cross its own "critical" cybersecurity risk threshold.

In a memo to staff, Altman said the government is "approving access customer by customer" during the preview period, and that a broader release could follow "a couple of weeks later" if the process goes well.

In a memo to staff, Altman said the government is "approving access customer by customer" during the preview period, and that a broader release could follow "a couple of weeks later" if the process goes well.

The OpenAI restrictions follow the Trump administration's <a target="_blank" rel="noopener noreferrer nofollow" href="https://www.verity.news/story/2026/trump-slaps-firstever-export-controls-on-anthropic-ai">export control directive against Anthropic</a>, which forced the company to pull its Mythos and Fable systems from public access. Negotiations over reinstating access to those systems remain ongoing.

The OpenAI restrictions follow the Trump administration's export control directive against Anthropic, which forced the company to pull its Mythos and Fable systems from public access. Negotiations over reinstating access to those systems remain ongoing.

Trump signed an executive order earlier in June directing AI companies to voluntarily submit advanced systems for government review up to 30 days before release, though the framework's specific rules have not yet been finalized.

Trump signed an executive order earlier in June directing AI companies to voluntarily submit advanced systems for government review up to 30 days before release, though the framework's specific rules have not yet been finalized.

Yahoo Finance #

CNBC #

R street #

CFR #

The Hill #

arXiv.org #

MS Now #

TechCrunch #

The Associated Press #

Guardian #

Axios #

Financial Times #

CNN #

The Washington Post #

Politico #

Slashdot #

Bloomberglaw #

Metaculus #

OpenAI announced Friday that its newest AI model, GPT-5.6 Sol, would be released only to a small group of government-approved partners, following a request from the Trump administration to limit the rollout amid concerns over the model's advanced cybersecurity capabilities.

OpenAI announced Friday that its newest AI model, GPT-5.6 Sol, would be released only to a small group of government-approved partners, following a request from the Trump administration to limit the rollout amid concerns over the model's advanced cybersecurity capabilities.

The staggered release was requested by the White House's Office of the National Cyber Director and Office of Science and Technology Policy. Commerce Secretary Howard Lutnick also spoke with OpenAI CEO Sam Altman on Wednesday, seeking assurances that all relevant agencies had tested and approved the model.

The staggered release was requested by the White House's Office of the National Cyber Director and Office of Science and Technology Policy. Commerce Secretary Howard Lutnick also spoke with OpenAI CEO Sam Altman on Wednesday, seeking assurances that all relevant agencies had tested and approved the model.

OpenAI said Sol is its most capable model to date, with improvements in coding, biology and cybersecurity. The company said the model is better at helping users identify and fix vulnerabilities than at carrying out attacks, and does not cross its own "critical" cybersecurity risk threshold.

OpenAI said Sol is its most capable model to date, with improvements in coding, biology and cybersecurity. The company said the model is better at helping users identify and fix vulnerabilities than at carrying out attacks, and does not cross its own "critical" cybersecurity risk threshold.

The OpenAI restrictions follow the Trump administration's <a target="_blank" rel="noopener noreferrer nofollow" href="https://www.verity.news/story/2026/trump-slaps-firstever-export-controls-on-anthropic-ai">export control directive against Anthropic</a>, which forced the company to pull its Mythos and Fable models from public access. Negotiations over reinstating access to those models remain ongoing.

The OpenAI restrictions follow the Trump administration's export control directive against Anthropic, which forced the company to pull its Mythos and Fable models from public access. Negotiations over reinstating access to those models remain ongoing.

Trump signed an executive order earlier in June directing AI companies to voluntarily submit advanced models for government review up to 30 days before release, though the framework's specific rules have not yet been finalized.

Trump signed an executive order earlier in June directing AI companies to voluntarily submit advanced models for government review up to 30 days before release, though the framework's specific rules have not yet been finalized.

The government now decides, customer by customer, who's allowed to buy a private company's product — under a framework whose actual rules haven't even been written yet. This is an example of the state inserting itself into the AI market as a gatekeeper, with no statute, no hearing, and no limit on how long "approved" stays optional.

The government now decides, customer by customer, who's allowed to buy a private company's product — under a framework whose actual rules haven't even been written yet. This is an example of the state inserting itself into the AI market as a gatekeeper, with no statute, no hearing, and no limit on how long "approved" stays optional.

Adam Thierer

Frontier AI models can autonomously exploit real-world software vulnerabilities, making this a national security necessity. A voluntary window is the minimum needed before adversaries weaponize the same capabilities. Without oversight, the U.S. risks shipping dangerous tools faster than it can defend against them.

Frontier AI models can autonomously exploit real-world software vulnerabilities, making this a national security necessity. A voluntary window is the minimum needed before adversaries weaponize the same capabilities. Without oversight, the U.S. risks shipping dangerous tools faster than it can defend against them.

There is an 85% chance that the U.S. will pass legislation that requires cybersecurity around AI models before 2030, according to the Metaculus prediction community.

There is an 85% chance that the U.S. will pass legislation that requires cybersecurity around AI models before 2030, according to the Metaculus prediction community.

AI: Warfare

AI: Geopolitics

AI: Safety and Regulations

Artificial Intelligence

Julia Demaree Nikhinson/Pool/AFP/Getty Images

OpenAI Limits GPT-5.6 Sol Release at White House Request

Politics

United States of America

Frontier AI systems can autonomously exploit real-world software vulnerabilities, making this a national security necessity. A voluntary window is the minimum needed before adversaries weaponize the same capabilities. Without oversight, the U.S. risks shipping dangerous tools faster than it can defend against them.

Frontier AI systems can autonomously exploit real-world software vulnerabilities, making this a national security necessity. A voluntary window is the minimum needed before adversaries weaponize the same capabilities. Without oversight, the U.S. risks shipping dangerous tools faster than it can defend against them.

There is an 85% chance that the U.S. will pass legislation that requires cybersecurity around AI systems before 2030, according to the Metaculus prediction community.

There is an 85% chance that the U.S. will pass legislation that requires cybersecurity around AI systems before 2030, according to the Metaculus prediction community.

OpenAI Limits GPT-5.6 Sol Release at White House Request

OpenAI Limits GPT-5.6 Sol Release at White House Request

The Spin

Metaculus Prediction

Public Figures

Go Deeper

Sign Up for Our Free Newsletters
Sign Up for Our Free Newsletters

OpenAI Limits GPT-5.6 Sol Release at White House Request

OpenAI Limits GPT-5.6 Sol Release at White House Request

The Spin

Metaculus Prediction

Public Figures

Go Deeper

Sign Up for Our Free NewslettersSign Up for Our Free Newsletters

Sign Up for Our Free Newsletters
Sign Up for Our Free Newsletters