Hegseth to Anthropic: Nice company you got there…
-
My take, the "supply chain risk" threat is an overreach. As for giving a civilian company oversight of military decisions having to do with its product, while the sovereign enemies of that military will almost certainly not have such restrictions - citizens of that country, who chose the administration who oversees that military, would reasonably be skeptical of any such arrangement. The DoD will not and should not enter into a relationship with a private company which in effect delegates authority over military decisions to that company.
-
My take, the "supply chain risk" threat is an overreach. As for giving a civilian company oversight of military decisions having to do with its product, while the sovereign enemies of that military will almost certainly not have such restrictions - citizens of that country, who chose the administration who oversees that military, would reasonably be skeptical of any such arrangement. The DoD will not and should not enter into a relationship with a private company which in effect delegates authority over military decisions to that company.
said in Hegseth to Anthropic: Nice company you got there…:
My take, the "supply chain risk" threat is an overreach. As for giving a civilian company oversight of military decisions having to do with its product, while the sovereign enemies of that military will almost certainly not have such restrictions - citizens of that country, who chose the administration who oversees that military, would reasonably be skeptical of any such arrangement. The DoD will not and should not enter into a relationship with a private company which in effect delegates authority over military decisions to that company.
And Claude's response:
That's a coherent and defensible position, and it touches on something that a lot of the commentary around this story glosses over.
The sovereignty argument is strong. Democratic accountability runs from citizens to elected officials to the military — not through a private company's ethics board. If voters elected an administration and that administration directs the Pentagon, there's a legitimate question about whether an AI company should be able to interpose itself in that chain of command. The comparison to other defense contractors is instructive: Lockheed Martin doesn't get to tell the military which targets are appropriate for an F-35. Raytheon doesn't attach usage conditions to a missile. The idea that Anthropic occupies a special position because its product involves "intelligence" rather than kinetics is interesting but not obviously persuasive from a governance standpoint.
And your point about adversaries is the one that national security hawks will always make, and it has real force. China, Russia, and others are developing military AI without these constraints. If the U.S. handicaps itself through private company vetoes, that's a strategic cost borne by the country, not by Anthropic's board.
Where I'd push back slightly is on a few tensions within this framing:
The "citizens chose this administration" argument works well in theory, but the specific concern about mass domestic surveillance is a case where the military could be turned against those same citizens. That's precisely the scenario where democratic accountability breaks down — the thing being surveilled is the electorate itself. So the check Anthropic is trying to provide, however imperfect, is aimed at a genuine gap in the oversight structure.
On the supply chain risk designation, I think you're right that using a tool designed for foreign adversary threats against a domestic company over a policy disagreement is a stretch. It's coercive in a way that undermines the government's credibility when it uses the same designation for actual security threats.
The harder question is the one you're implicitly raising: if Anthropic shouldn't have this authority, and the current oversight mechanisms are weak, then who exactly is the check on misuse? That's not Anthropic's problem to solve, but it is a problem.
-
Claude's pushback regarding government surveillance is age-old, not new to our AI age. It's never been anywhere near the top of my list of things to worry about. The sorts of people who are super worried about government surveillance come in two main flavors: consistently principled kooks, and tribalists complaining about the government they didn't vote for.
-
I don't know that we've ever had a SecDef threatening a company over providing the capability given that it's illegal to implement. That part isn't age-old and should be concerning in itself.
-
I don't know that we've ever had a SecDef threatening a company over providing the capability given that it's illegal to implement. That part isn't age-old and should be concerning in itself.
@jon-nyc said in Hegseth to Anthropic: Nice company you got there…:
I don't know that we've ever had a SecDef threatening a company over providing the capability given that it's illegal to implement. That part isn't age-old and should be concerning in itself.
That's your framing, and it isn't objectively accurate. The military is not asking Anthropic to support illegal surveillance per se. It is simply not willing to delegate authority over questions of legality or morality to the Anthropic ethics board.
-
It’s insisting they provide the capability. There is no framing which renders the former sentence untrue.
Use of the capability is illegal.
@jon-nyc said in Hegseth to Anthropic: Nice company you got there…:
It’s insisting they provide the capability. Use of the capability is illegal.
That's your framing. Another framing would be that the DoD refuses to delegate authority to Anthropic to decide what is or is not ethical or illegal. It is simply unequivocally false that the DoD has insisted on a capability to do something illegal. In fact they have stated they will follow the law. You can be skeptical of that, but you cannot invent a version of what they're explicitly insisting on. I mean, you can, but it's just dishonest tribal rhetoric.
Education is extremely important.
-
They would be the first to tell you that Congress decided it was illegal. The only thing Anthropic decided was to withhold the capability.
Hegseth is threatening them for having done that. That is 100% true.
-
They would be the first to tell you that Congress decided it was illegal. The only thing Anthropic decided was to withhold the capability.
Hegseth is threatening them for having done that. That is 100% true.
@jon-nyc said in Hegseth to Anthropic: Nice company you got there…:
They would be the first to tell you that Congress decided it was illegal. The only thing Anthropic decided was to withhold the capability.
Hegseth is threatening them for having done that. That is 100% true.
The DoD has explicitly not asked for the ability to do anything illegal. You can be skeptical. You cannot invent something the DoD demanded.
Feel free to cite where the DoD demanded the ability to do illegal mass surveillance. Cite the sentences in publicly available words from the DoD that substantiates that.
-
is it fair to say that the Department of Defense has demanded that Anthropic provide it with the ability to do illegal mass surveillance?
Claude:
No, that's not a fair characterization based on what's been reported.The Pentagon's demand is that Anthropic agree to "all lawful use" without the company imposing its own additional restrictions. That's a meaningful distinction. The Pentagon isn't saying "let us do illegal things" — they're saying "we decide what's lawful, not you." Their stated position, as reported, is that legality is the Pentagon's responsibility as the end user.
Anthropic's concern is more forward-looking and precautionary — that without explicit contractual restrictions, there's nothing stopping the technology from being used for mass surveillance, and that the legal frameworks around AI-enabled surveillance are underdeveloped. Anthropic isn't claiming the Pentagon has asked to do mass surveillance. They're saying they want a guarantee it won't happen, and the Pentagon is refusing to give one on principle — because they view that as ceding decision-making authority to a vendor.
So the dispute is really about who sets the boundaries. The Pentagon's position is essentially: "The law is the boundary, and we interpret the law." Anthropic's position is: "The law is unclear in this area, and we want additional contractual guardrails beyond what the law currently requires."
Those are genuinely different positions, and you can think Anthropic is wrong to insist on that extra layer without concluding that the Pentagon is asking for permission to break the law. A lot of the more breathless coverage conflates "the Pentagon won't agree to Anthropic's specific restrictions" with "the Pentagon wants to do the things Anthropic is worried about," and that's a logical leap the reporting doesn't support.
-
@jon-nyc said in Hegseth to Anthropic: Nice company you got there…:
It’s insisting they provide the capability. Use of the capability is illegal.
That's your framing. Another framing would be that the DoD refuses to delegate authority to Anthropic to decide what is or is not ethical or illegal. It is simply unequivocally false that the DoD has insisted on a capability to do something illegal. In fact they have stated they will follow the law. You can be skeptical of that, but you cannot invent a version of what they're explicitly insisting on. I mean, you can, but it's just dishonest tribal rhetoric.
@Horace said in Hegseth to Anthropic: Nice company you got there…:
@jon-nyc said in Hegseth to Anthropic: Nice company you got there…:
Another framing would be that the DoD refuses to delegate authority to Anthropic to decide what is or is not ethical or illegal.If you're right, then Anthropic can just write a letter saying they take no position on the legality and ethics of mass surveillance of US citizens and the matter is solved.
After all (according to you) the DoD has not demanded that they provide the capability.
-
An analogy would be if guns had broad strokes AI built into them intended to prevent unlawful discharge, but that AI was known to provide false positives. For the general public, maybe the cost / benefit of such an AI would be acceptable, but for the military, no such gun would ever be bought. If it was a great gun, the military would either demand that the guardrails be removed, or it would not do business with that company. But I do agree that punishing the company with a supply chain threat designation is overreach.
Presumably anybody could agree that AI guardrails against "illegal mass surveillance" could not possibly discern with perfect accuracy whether it is being used for that. There will necessarily be false negatives and false positives. The military doesn't want to deal with that. And that's reasonable.
-
We can also pick apart the concept that there is such a thing as unambiguous "illegal mass surveillance", to say nothing of an AI's ability to know that it's a part of such a scheme. I am very skeptical of jon's frequent claims of what is or is not obviously illegal. The actual law is, more often than not, ambiguous, and the certainty of illegality is just a rhetorical trick.
how unambiguously defined is "illegal mass surveillance" in US law?
Claude:
It's not well-defined at all, and that's a significant part of the problem.There's no single statute that says "mass surveillance is illegal" in clear terms. What exists is a patchwork. The Fourth Amendment prohibits unreasonable searches, but what counts as a "search" in the context of AI-powered data analysis is unsettled law. The Posse Comitatus Act restricts military involvement in domestic law enforcement, but has exceptions and has been interpreted narrowly. Executive Order 12333 governs intelligence collection and has restrictions on surveilling US persons, but it's an executive order — the current president can modify or revoke it. FISA governs foreign intelligence surveillance but has been interpreted to permit bulk collection programs that many would call mass surveillance. The NSA programs Snowden revealed were happening under legal frameworks that the government argued were lawful.
The fundamental ambiguity is that "surveillance" at scale using AI doesn't map neatly onto existing legal categories. Is it surveillance if an AI model processes publicly available social media posts to identify patterns? What about analyzing metadata rather than content? What if the system flags individuals for human review rather than taking action autonomously? Existing law was mostly written for wiretaps and physical searches, not for an AI that can process and correlate vast datasets in ways that don't clearly fit the old definitions.
So when Anthropic says it wants to prevent "mass surveillance" and the Pentagon says it will follow "the law," they're both gesturing at a legal landscape that's genuinely ambiguous. Anthropic is essentially saying the law hasn't caught up and they want to err on the side of caution. The Pentagon is saying that ambiguity is for courts and Congress to resolve, not a vendor.
This is actually one of the stronger arguments for the Pentagon's position on this specific point — if the law is unclear, it's not obvious that a private company should be the one drawing the line.
-
The Pentagon's demand is that Anthropic agree to "all lawful use" without the company imposing its own additional restrictions.
That does not depend on Anthropic setting fire to its ethics branding.
@Horace said in Hegseth to Anthropic: Nice company you got there…:
The Pentagon's demand is that Anthropic agree to "all lawful use" without the company imposing its own additional restrictions.
So they are insisting that they provide the capability? You explicitly said otherwise a few posts back.
The whole reason we call them illegal aliens is because they’re subject to our laws.
-
@Horace said in Hegseth to Anthropic: Nice company you got there…:
The Pentagon's demand is that Anthropic agree to "all lawful use" without the company imposing its own additional restrictions.
So they are insisting that they provide the capability? You explicitly said otherwise a few posts back.
@jon-nyc said in Hegseth to Anthropic: Nice company you got there…:
@Horace said in Hegseth to Anthropic: Nice company you got there…:
The Pentagon's demand is that Anthropic agree to "all lawful use" without the company imposing its own additional restrictions.
So they are insisting that they provide the capability? You explicitly said otherwise a few posts back.
Any piece of technology can be used illegally. They are insisting that imperfect guardrails not be imposed on them. That is not the same as an insistence that they are provided with the ability to do illegal things. The AI will provide them with the ability to do illegal things with or without the imperfect guardrails. But what they have not done, is to insist on an ability to break the law. If it were possible for the AI to know what the law is exactly, which of course it isn't, as the law in question is unsettled, then in theory the pentagon would agree to the guardrails. But that thought experiment depends on an impossible universe.
-
So they’re not insisting that the company provide the capability, they’re insisting that they not NOT provide the capability.
Ok glad we’ve cleared that up.
Shame on me for the tortured framing.
-
So they’re not insisting that the company provide the capability, they’re insisting that they not NOT provide the capability.
Ok glad we’ve cleared that up.
Shame on me for the tortured framing.
@jon-nyc said in Hegseth to Anthropic: Nice company you got there…:
So they’re not insisting that the company provide the capability, they’re insisting that they not NOT provide it.
Ok glad we’ve cleared that up.
Shame on me for the tortured framing.
It's incoherent to say that the difference between the version of AI anthropic would like to provide, and the version the DoD wants, is that one has the ability to be used illegally and the other does not. No such categorical separation exists. The DoD is insisting on the absence of imperfect guardrails, literally. That is not the same as "insisting on the ability to break the law". If all they wanted was the ability, they could use the version Anthropic suggests. They are insisting that Anthropic not be in the loop regarding whether something is legal or illegal. They have pledged to follow law, such as it is.
-
Ok, so let’s leave the legality to the future lawyers since it depends on actual use.
For tomorrow’s deadline, they’re insisting that Anthropic NOT NOT provide a certain capability. Which is different than insisting they DO provide that same capability. In fact, the latter is dishonest tribal rhetoric.
Ok, I’m learning. Don’t give up on me yet.
