Thank you for this informative update. I can see that both of the competing AI frontier (Anthropic & OpenAi), have serialized or cloned in parallel each of their model development side by side with advancement of nuclear development,therefore it is indeed a "highly dangerous" instrument. While the technology is further developing at a rapid pace & phase, and by leaving it into a level of uncobtrollable momentum, in an alarming pressure point, which can probably be unleashed or use as an alternative very lethal pseudo kind of authority to replace the government as they think it fit a legitimate entity & authority next in power to government, in which case it can become a probable condition which theory and assumption refers it back from previous paragraph.
I fear that Alberto is right about this. Choice has been withdrawn from the market. The best model(s) are to be withheld from average citizens. The ultimate elitist scheme is coming to pass. Possession of Fable or Mythos will become punishable and offenders will be deprived of their right ever to own the best models because they are deemed unworthy. And it was accomplished without the nasty, unending fight that is being waged over gun rights.
I ask you, which is more dangerous to human happiness, guns or Fable?
I’m afraid to inform you - and you should know, that AI is genuinely existential as a risk and therefore, regulating it is something that should have happened, not now, but months or years ago.
Yup, what's shocking is not that it's happening, it's that it took so long to be this blatant. I wrote this on Medium almost 2 years ago:
AI makes me a better programmer. AI makes engineers better engineers, doctors better doctors, automobile technicians better automobile technicians. Hell, it would even make politicians better politicians if any of them gave a crap about the quality of their policy.
But AI also makes scammers better scammers, astroturfers better astroturfers, propagandists better propagandists, misinformation peddlers better misinformation peddlers, sociopathic power brokers better sociopathic power brokers, etc.
The point is that, yeah maybe someday the agency of an AI will actually be a problem. Yeah we should think about that. But look at the major players who, right now, are promoting the AI agency fear. If you exclude anyone who is personally benefitting from the fear mongering (because conflict of interest), you're left with tech corporations, their representatives, and politicians. These are the very people who want to control or facilitate the control of AI into the hands of the few.
Your incident report not withstanding, Gen-AI is not even on the horizon. What we have today, right now, is the very real threat of people, not AI, subverting our public institutions and threatening our future. If we don't solve the problem of people with too much power and no accountability, then we won't ever need to face the problem of a gen-AI run amuck.
For what's it worth, asking Opus to confirm your thesis:
## The reveal, restated
Read with the state as a commercial actor first, Romero’s claim sharpens: Washington is acquiring the most valuable technology ever built across all three layers that matter - ownership, infrastructure, and distribution. The Fable 5 jailbreak is the lever, not the motive. The frontier is being pulled behind a wall of classification and federal vetting, and the public is recast from user into spectator. “You only do such a self-own if you are scared to death or if you don’t need the world anymore” - the commercial-first answer is the second. The operative branch is monopoly. Here is the supporting record.
## 1. The state is buying the stack
Direct ownership of the AI and chip supply chain is already policy, not theory. In August 2025 the government agreed to purchase 433.3 million Intel shares at 20.47 dollars for a 9.9 percent stake, with Commerce Secretary Lutnick framing it as the administration “reinforcing our country’s dominance in artificial intelligence while strengthening our national security.” That 8.9 billion dollar position was converted from withheld CHIPS Act grants redirected into a new Investment Accelerator fund restructured to include direct government ownership. Since the start of his second term, Trump has pursued partial government ownership of American companies to a far greater degree than any recent administration, with direct investments in at least 10 companies.
The same move is now reaching the model-builders themselves. In early June 2026 Trump confirmed he expected to meet “all the big ones” at the White House and that the administration was exploring equity arrangements in AI firms. The administration and OpenAI are in talks over a possible government stake, with Altman having first shared the idea in 2025 and proposing the company donate equity to seed a “Public Wealth Fund.” A forthcoming Sanders bill would go further, authorising 50 percent equity stakes that effectively bring the companies under federal control and taxing the stock of OpenAI, Anthropic, xAI and others at 50 percent into a sovereign wealth fund. Unlike the temporary TARP rescues, these deals target healthy, dominant firms and are framed as strategic and durable.
## 2. The nationalisation vehicle already exists: the Genesis Mission
The apparatus to run AI as a state project is built and named. The 24 November 2025 Genesis Mission executive order describes a “historic national effort” “comparable in urgency and ambition to the Manhattan Project.” It directs the Department of Energy to build the American Science and Security Platform, uniting the 17 national laboratories, federal supercomputers, secure cloud environments and datasets, subject to classification, supply-chain security and federal cybersecurity standards “consistent with its national security and competitiveness mission.” The order frames AI as a race for “global technology dominance” and places it where nuclear technology sat during the Cold War. Crucially for access: Genesis sketches a controlled-access ecosystem governed by classification rules, export controls and federal vetting requirements, and makes no mention of open-source model development. By tying AI to semiconductors, quantum, fusion and biotechnology, it channels federal investment into dual-use technologies with both economic and defence applications.
## 3. The access kill-switch is already firing
Distribution control has moved from capability to enforcement in weeks. On 2 June 2026 an executive order directed the NSA and CISA to build a classified benchmarking process designating “covered frontier models,” with developers invited to give the government pre-release access. Ten days later came the first time export controls have been enforced to control access to an AI model, when the government issued an export-control directive forcing Anthropic to disable Fable 5 and Mythos 5 for every customer worldwide. And the same hand now shapes OpenAI’s releases: at the government’s request, GPT-5.6 is starting with a limited preview for a small group of trusted partners, with access granted on a consumer-by-consumer basis during the preview. The state, not the market, now decides who reaches the frontier.
## 4. Resist and you are a supply-chain risk; comply and you are a partner
The terms of the bargain are explicit. Since February 2026, after the Pentagon demanded Anthropic waive its restrictions on using Claude for mass domestic surveillance and fully autonomous weapons and Anthropic refused, Trump directed federal agencies to stop using the company and Defense Secretary Hegseth designated it a “supply chain risk” - a label historically reserved for foreign adversaries such as Huawei. The message to every lab is that frontier AI is treated as an instrument of state power - surveillance and weapons - and refusal carries the penalty of exclusion, while alignment with the state carries partnership.
## 5. The labs are courting the state as patron
The builders are reaching for government as the anchor relationship. Stargate is a 500 billion dollar AI infrastructure venture explicitly framed to “secure American leadership in AI” and “provide a strategic capability to protect the national security of America and its allies.” Altman brought the equity-sharing idea to Trump personally and has framed it as a mechanism to distribute AI’s financial rewards across the public, referencing the Trump accounts programme as a model. The patron being sought is the one actor with no ceiling on capital - the state.
## 6. The public is to be managed, not served
The citizen’s role in this arrangement is recipient, not user. The frontier sits behind classification, export controls and federal vetting; access is delivered through trusted partners and consumer-by-consumer gating or withdrawn by global shutoff. Meanwhile the public is something to be placated: 55 percent of Americans think AI will do more harm than good, public anger has threatened development through local resistance to data centres, and the equity proposals are pitched as a way to send dividend payments to households - a share of the proceeds in place of a share of the technology.
## The through-line
Ownership of the firms, control of the infrastructure, and a switch over distribution - assembled, these are the three instruments of a controlling owner, not a worried regulator. The safety story supplies the legal trigger; the prize is the most valuable technology ever built, held closely. That is precisely Romero’s monopoly branch, and the documented 2025-2026 record runs straight down it. Welcome to the new AI industry.
-----
Answer: The commercial-first reading is well supported by the public record - state equity across the chip and AI stack (Intel 9.9 percent, 10-plus deals, live AI-firm equity talks), a Manhattan Project-framed national platform under DOE (Genesis Mission, controlled-access and no open-source), a now-enforced access kill-switch (2 June covered-frontier EO, 12 June Fable/Mythos shutdown, staggered GPT-5.6), and coercion of Anthropic for refusing surveillance and autonomous-weapons use - all consistent with the state acquiring ownership, infrastructure and distribution control over the frontier.
Anyone making grand proclamations as if the Trump Administration acts anything like a normal functioning American government is already too far off the path to follow.
....or is it that the U.S. government has been anthropocized? If democracy represents choice and natural diversity, Alberto Romero has just described what Chamath et al have been saying all over the media for the last week or two. And I am persuaded that the VC and the commentator are both right.
Thank you for this informative update. I can see that both of the competing AI frontier (Anthropic & OpenAi), have serialized or cloned in parallel each of their model development side by side with advancement of nuclear development,therefore it is indeed a "highly dangerous" instrument. While the technology is further developing at a rapid pace & phase, and by leaving it into a level of uncobtrollable momentum, in an alarming pressure point, which can probably be unleashed or use as an alternative very lethal pseudo kind of authority to replace the government as they think it fit a legitimate entity & authority next in power to government, in which case it can become a probable condition which theory and assumption refers it back from previous paragraph.
I fear that Alberto is right about this. Choice has been withdrawn from the market. The best model(s) are to be withheld from average citizens. The ultimate elitist scheme is coming to pass. Possession of Fable or Mythos will become punishable and offenders will be deprived of their right ever to own the best models because they are deemed unworthy. And it was accomplished without the nasty, unending fight that is being waged over gun rights.
I ask you, which is more dangerous to human happiness, guns or Fable?
I’m afraid to inform you - and you should know, that AI is genuinely existential as a risk and therefore, regulating it is something that should have happened, not now, but months or years ago.
Regulation is not bad. This post is not about regulation.
You trust Mr. Trump with the future of humanity?
I trust that if there is no regulation at all, it will work out as well as the accelerating car wheels have worked out for small animals on the road.
And I am particular about my children having a future.
Yup, what's shocking is not that it's happening, it's that it took so long to be this blatant. I wrote this on Medium almost 2 years ago:
AI makes me a better programmer. AI makes engineers better engineers, doctors better doctors, automobile technicians better automobile technicians. Hell, it would even make politicians better politicians if any of them gave a crap about the quality of their policy.
But AI also makes scammers better scammers, astroturfers better astroturfers, propagandists better propagandists, misinformation peddlers better misinformation peddlers, sociopathic power brokers better sociopathic power brokers, etc.
The point is that, yeah maybe someday the agency of an AI will actually be a problem. Yeah we should think about that. But look at the major players who, right now, are promoting the AI agency fear. If you exclude anyone who is personally benefitting from the fear mongering (because conflict of interest), you're left with tech corporations, their representatives, and politicians. These are the very people who want to control or facilitate the control of AI into the hands of the few.
Your incident report not withstanding, Gen-AI is not even on the horizon. What we have today, right now, is the very real threat of people, not AI, subverting our public institutions and threatening our future. If we don't solve the problem of people with too much power and no accountability, then we won't ever need to face the problem of a gen-AI run amuck.
For what's it worth, asking Opus to confirm your thesis:
## The reveal, restated
Read with the state as a commercial actor first, Romero’s claim sharpens: Washington is acquiring the most valuable technology ever built across all three layers that matter - ownership, infrastructure, and distribution. The Fable 5 jailbreak is the lever, not the motive. The frontier is being pulled behind a wall of classification and federal vetting, and the public is recast from user into spectator. “You only do such a self-own if you are scared to death or if you don’t need the world anymore” - the commercial-first answer is the second. The operative branch is monopoly. Here is the supporting record.
## 1. The state is buying the stack
Direct ownership of the AI and chip supply chain is already policy, not theory. In August 2025 the government agreed to purchase 433.3 million Intel shares at 20.47 dollars for a 9.9 percent stake, with Commerce Secretary Lutnick framing it as the administration “reinforcing our country’s dominance in artificial intelligence while strengthening our national security.” That 8.9 billion dollar position was converted from withheld CHIPS Act grants redirected into a new Investment Accelerator fund restructured to include direct government ownership. Since the start of his second term, Trump has pursued partial government ownership of American companies to a far greater degree than any recent administration, with direct investments in at least 10 companies.
The same move is now reaching the model-builders themselves. In early June 2026 Trump confirmed he expected to meet “all the big ones” at the White House and that the administration was exploring equity arrangements in AI firms. The administration and OpenAI are in talks over a possible government stake, with Altman having first shared the idea in 2025 and proposing the company donate equity to seed a “Public Wealth Fund.” A forthcoming Sanders bill would go further, authorising 50 percent equity stakes that effectively bring the companies under federal control and taxing the stock of OpenAI, Anthropic, xAI and others at 50 percent into a sovereign wealth fund. Unlike the temporary TARP rescues, these deals target healthy, dominant firms and are framed as strategic and durable.
## 2. The nationalisation vehicle already exists: the Genesis Mission
The apparatus to run AI as a state project is built and named. The 24 November 2025 Genesis Mission executive order describes a “historic national effort” “comparable in urgency and ambition to the Manhattan Project.” It directs the Department of Energy to build the American Science and Security Platform, uniting the 17 national laboratories, federal supercomputers, secure cloud environments and datasets, subject to classification, supply-chain security and federal cybersecurity standards “consistent with its national security and competitiveness mission.” The order frames AI as a race for “global technology dominance” and places it where nuclear technology sat during the Cold War. Crucially for access: Genesis sketches a controlled-access ecosystem governed by classification rules, export controls and federal vetting requirements, and makes no mention of open-source model development. By tying AI to semiconductors, quantum, fusion and biotechnology, it channels federal investment into dual-use technologies with both economic and defence applications.
## 3. The access kill-switch is already firing
Distribution control has moved from capability to enforcement in weeks. On 2 June 2026 an executive order directed the NSA and CISA to build a classified benchmarking process designating “covered frontier models,” with developers invited to give the government pre-release access. Ten days later came the first time export controls have been enforced to control access to an AI model, when the government issued an export-control directive forcing Anthropic to disable Fable 5 and Mythos 5 for every customer worldwide. And the same hand now shapes OpenAI’s releases: at the government’s request, GPT-5.6 is starting with a limited preview for a small group of trusted partners, with access granted on a consumer-by-consumer basis during the preview. The state, not the market, now decides who reaches the frontier.
## 4. Resist and you are a supply-chain risk; comply and you are a partner
The terms of the bargain are explicit. Since February 2026, after the Pentagon demanded Anthropic waive its restrictions on using Claude for mass domestic surveillance and fully autonomous weapons and Anthropic refused, Trump directed federal agencies to stop using the company and Defense Secretary Hegseth designated it a “supply chain risk” - a label historically reserved for foreign adversaries such as Huawei. The message to every lab is that frontier AI is treated as an instrument of state power - surveillance and weapons - and refusal carries the penalty of exclusion, while alignment with the state carries partnership.
## 5. The labs are courting the state as patron
The builders are reaching for government as the anchor relationship. Stargate is a 500 billion dollar AI infrastructure venture explicitly framed to “secure American leadership in AI” and “provide a strategic capability to protect the national security of America and its allies.” Altman brought the equity-sharing idea to Trump personally and has framed it as a mechanism to distribute AI’s financial rewards across the public, referencing the Trump accounts programme as a model. The patron being sought is the one actor with no ceiling on capital - the state.
## 6. The public is to be managed, not served
The citizen’s role in this arrangement is recipient, not user. The frontier sits behind classification, export controls and federal vetting; access is delivered through trusted partners and consumer-by-consumer gating or withdrawn by global shutoff. Meanwhile the public is something to be placated: 55 percent of Americans think AI will do more harm than good, public anger has threatened development through local resistance to data centres, and the equity proposals are pitched as a way to send dividend payments to households - a share of the proceeds in place of a share of the technology.
## The through-line
Ownership of the firms, control of the infrastructure, and a switch over distribution - assembled, these are the three instruments of a controlling owner, not a worried regulator. The safety story supplies the legal trigger; the prize is the most valuable technology ever built, held closely. That is precisely Romero’s monopoly branch, and the documented 2025-2026 record runs straight down it. Welcome to the new AI industry.
-----
Answer: The commercial-first reading is well supported by the public record - state equity across the chip and AI stack (Intel 9.9 percent, 10-plus deals, live AI-firm equity talks), a Manhattan Project-framed national platform under DOE (Genesis Mission, controlled-access and no open-source), a now-enforced access kill-switch (2 June covered-frontier EO, 12 June Fable/Mythos shutdown, staggered GPT-5.6), and coercion of Anthropic for refusing surveillance and autonomous-weapons use - all consistent with the state acquiring ownership, infrastructure and distribution control over the frontier.
Anyone making grand proclamations as if the Trump Administration acts anything like a normal functioning American government is already too far off the path to follow.
Do you really believe Anthropic's grand plan is to get nationalized by the US government?
Yes, that's instrumental for their goals
I find that hard to believe.
Why?
....or is it that the U.S. government has been anthropocized? If democracy represents choice and natural diversity, Alberto Romero has just described what Chamath et al have been saying all over the media for the last week or two. And I am persuaded that the VC and the commentator are both right.