Dear Alex,
F**k off
Kind regards, Everyone
Palantir had a whopper of a Q4, showing accelerating revenue growth, beating Wall Street's profit estimates, and enjoying a share price jump of as much as 11% during pre-market trading on Tuesday before coming back down to earth. At such a triumphal moment, it was striking that the company was forced on the defensive, not …
Does he care?
The ROI of the few million he bunged to a certain President will overjoy his techbro investors as government contracts shoot up and not just in Minnesota. Here in return for all our data they might help the NHS do something or other. And we are paying for it!
https://www.axios.com/local/denver/2025/10/23/palantir-donation-trump-white-house-ballroom
Of *course* he cares. Whilst helping to implement 1984-style society-wide surveillance that his company is founded on, he is also trying to forward a belief that selling you even more of his company's services will help mitigate the loss of civil rights.
He is, both without question and at a historical record-breaking level, being an absolute hypocrite but hopes that you don't notice, or at the minimum go along with the plan.
'If we sell our surveillance aggregation services to big governments we'll make a fortune providing them data. If we sell our surveillance aggregation services to small municipalities with beliefs that doing so will help maintain Fourth Amendment balance we will make a fortune. And if we get the public being surveilled that this is the best possible outcome for them, plus support the budget implementations necessary to pay for our governmental services, we'll make even MORE of a fortune!'
This is American Greed brought to the next-level, without even the innuendo of a hint of a concern for anyone else but their own pockets.
But why should I be surprised? Big Tech has actually bought George Orwell's fears to life but it's been declared "OK" because someone is making money off of it.
You're right, we should buy more.
I suggest moving $70b or more from DHS to IRS and feeding Palantir everything about the tax dodges in use across corporate America, and maybe encourage some corner cutting at the administrative tax courts to raise some revenue.
Maybe we could find a $25b or so to add a ton of Palantir to ATF as well, maybe clean up the gun situation on a political basis, or Dept of Interior to nail those free range scofflaws on the western prairies, or hey, the Federal Election Commission and really tear up the dark money lobbying and campaign finance scene.
What most of these idealogues fail to see is anything past the end of this administration. There's some assumption that there will be no repercussions from this stuff, which is both troubling in its moronic simplicity and incredibly troubling in its dark implications for democracy and free elections. Blech.
But why should I be surprised? Big Tech has actually bought George Orwell's fears to life but it's been declared "OK" because someone is making money off of it.
You have simply misunderstood. Palantir protects your rights by holding them for you. They will tell you when you can use them. An officer from Minitrue will be by to 'escort' you to re-education.
We were part of a rainbow team looking at the need for some analytics for a specific part of Defence. We were reporting into a prime. The prime (A****) told us quite clearly that they had a strategic alliance with Palantir and estimated that future work related to these analytics would be worth 70 million. The report had to say that. There was never any concept of this being an objective study. We found that there was absolutely no benefit and need for the said analytics. Guess how many revisions of the report there were and what it eventually recommended?
On a lark, I asked Copilot how AI is being used to usher in an era of total global surveillance. Here's what it had to say:
How Artificial Intelligence Is Helping Usher in an Era of Total Global Surveillance
Artificial intelligence is rapidly transforming the scope, speed, and scale of surveillance worldwide. While surveillance itself is not new, AI is fundamentally changing how much governments and institutions can see, interpret, and act upon—often in real time, and with far fewer human constraints.
This shift is occurring through several intertwined mechanisms:
1. AI Supercharges Traditional Surveillance Infrastructure
Facial Recognition at Scale
AI-driven facial recognition transforms static CCTV networks into active tracking systems capable of identifying individuals across entire cities. This allows authorities to continuously match faces against massive databases and track movement patterns in real time, something impossible with human-only monitoring.
Countries such as Malaysia, Singapore, China, and many others have deployed or planned widespread systems that integrate cameras, facial recognition, and centralized AI analysis engines.
Context-Aware Video Analytics
Beyond simple identification, modern AI surveillance tools can assess behavior, crowd density, environmental context, and even predicted actions—providing a level of interpretation that previously required teams of analysts.
This can include recognizing specific clothing, detecting unusual movements, and producing automatic alerts, vastly expanding state monitoring capabilities.
2. Global Proliferation of AI Surveillance Technologies
The AI Global Surveillance Index tracks adoption of AI-enhanced monitoring tools in 176 countries, revealing an unprecedented international surge.
These deployments range from:
Smart city platforms
Predictive policing systems
Biometric border control
Ubiquitous traffic and pedestrian monitoring
Countries of every regime type—liberal democracies, electoral democracies, autocracies—are adopting these systems, demonstrating a global normalization of AI-powered surveillance.
3. AI Lowers the Cost of Authoritarian Control
AI enables governments to monitor citizens without the expense of large security forces, thereby empowering both cash-strapped states and established autocracies.
Examples:
AI surveillance can detect dissent, track protestors, and identify critics online or in public spaces with unprecedented speed.
Research indicates that simply knowing such systems exist can reduce public protest, creating a chilling effect.
This dynamic allows regimes to exert control more subtly and with fewer visible acts of repression—making modern authoritarianism less visibly violent but more structurally pervasive.
4. AI Surveillance Is Expanding Across Democracies Too
Surveillance abuses are no longer confined to authoritarian states. Even in the United States, concerns have grown about government agencies and contractors using AI tools to:
Scan social media at massive scale
Summarize millions of posts for intelligence purposes
The combination of vast data, political polarization, and weak oversight creates an environment where advanced monitoring tools can be misused by state actors.
5. Blurring of State Sovereignty Through Cross‑Border AI Surveillance
AI surveillance technologies increasingly cross national borders, allowing one country’s tools to monitor individuals within another nation.
For example:
Spyware such as Pegasus and advanced facial recognition systems developed in the U.S., China, or Israel can be deployed globally.
This erodes traditional notions of territorial sovereignty and enables states to conduct surveillance without any physical presence.
Such cross-border surveillance raises major ethical, diplomatic, and human rights concerns.
6. Public Adoption of AI‑Enhanced “Convenience” Systems
Some surveillance expansion happens indirectly, through consumer-facing AI tools marketed as efficiency innovations—such as biometric travel systems, smart city apps, and frictionless authentication services.
People often adopt them without fully understanding the implications for:
Data retention
Privacy protection
State access to sensitive biometric data
This contributes to a normalization of biometric monitoring in everyday life.
7. Corporate and Financial Sector Integration of AI Surveillance
AI is also transforming corporate surveillance, especially in financial and communications monitoring. Regulators increasingly expect AI-enhanced tools to detect risks and misconduct, leading firms to adopt sophisticated monitoring platforms that analyze communications at scale.
As these systems proliferate, the line between government surveillance and private-sector surveillance becomes increasingly blurred.
Conclusion: AI Enables a New Level of Global Surveillance
Together, these developments suggest that AI is not just augmenting traditional surveillance—it is enabling a qualitatively new era characterized by:
Real-time monitoring of entire populations
Predictive analysis of behaviors and dissent
Cross-border intrusion into sovereign domains
Mass data aggregation beyond human comprehension
Reduced costs and increased automation of state control mechanisms
Modern AI technologies have created the infrastructure for continuous, global, automated observation—a capability once considered science fiction.
Quite.
Now ask it how AI is helping to protect the privacy, safety and rights of ordinary people from state interference in their lives and watch it come up with a similarly plausible word salad of total bollocks to support that proposition.
The more that I see and hear with regard to the current crop of LLM 'AI', the more it becomes apparent that they will provide you with whatever answer the wording of your query gives the impression that you are hoping for.
I did that, and the difference in the results is striking. Most of the answers which came back refer to how AI is being regulated to control it and create legal guardrails. The one exception is that human rights organizations are using AI tools to monitor for human rights abuses. Copilot misconstrues limitations being put on AI as AI being used to protect human rights, which is clearly incorrect, but the results were not gibberish.
Chat.deepseek.com is a wonderful way to find out how LLMs could be limited to party line responses... Ask it "What real people have been compared with Winnie the Pooh?"
The beginning of an answer streams across, up until it mentions 'Winnie the Pooh', and the response is instantly replaced with "Sorry, that's beyond my current scope. Let’s talk about something else."
I ran Co Pilot’s analysis past ChstGPT. It agrees with much of Co Pilot but where it doesn’t, it says:
“ Where Copilot overreaches or blurs distinctions
4. “Real-time monitoring of entire populations” — not quite
This is the biggest exaggeration.
What exists today is:
• real-time sensor ingestion
• delayed analysis
• selective intervention
The bottleneck has moved, but it still exists:
• legal authorisation
• institutional capacity
• false positives
• political risk
AI creates continuous data exhaust, not continuous human attention or action.
That distinction matters.
⸻
5. Predictive policing is weaker than implied
Predictive systems are far better at:
• reinforcing existing biases
• optimising patrol routes
• flagging “known” patterns
They are not reliably good at discovering novel dissent or predicting genuine political rupture.
States still miss revolutions.
They still misread intent.
They still overfit to yesterday.
AI stabilises, it does not guarantee foresight.
⸻
6. Cross-border surveillance isn’t new — automation is
Spyware like Pegasus is framed as revolutionary, but intelligence agencies have always spied extraterritorially.
What is new:
• speed of deployment
• deniability
• commercialisation
The danger isn’t sovereignty collapse per se — it’s privatised intelligence power without democratic constraint.
That’s a subtler, nastier shift than Copilot fully articulates.
⸻
The part Copilot underplays (and this is key)
The real danger is pipeline logic
The most important missing concept is this:
AI surveillance systems don’t just observe — they route people into administrative consequences.
Not arrests.
Not prisons.
But:
• benefit reviews
• travel flags
• visa delays
• account closures
• employment screening
• “risk” designations
This is governance by silent friction, not force.
The threat is not a police state.
It’s a bureaucratic exclusion state.
⸻
Corporate–state fusion is the real frontier
Copilot gestures at this but doesn’t land it.
What’s emerging is:
• state legitimacy
• corporate infrastructure
• automated decision-making
• weak contestability
This produces power without accountability or visibility.
No jackboots.
No secret police.
Just systems that say: computer says no.
⸻
My bottom-line judgement
Copilot is right about the direction, wrong about the arrival point.
We are not in:
“total global surveillance”
We are in:
pre-emptive governance via machine-mediated selection
The historical analogy isn’t Orwell.
It’s credit scoring + border control + welfare conditionality + risk analytics, fused into a single logic.
That is more boring.
More legal.
More invisible.
And far harder to resist.”
When I was a lot younger, I had this argument with the NatWest because somebody entered by date of birth incorrectly and they were quite unwilling to change it - because the computer says...
Mind you the manager of that branch was really quite dim. When my mother was vouching for my correct date of birth, he said "and how would you know when he was born?". Mom just glared and let the stupid echo the room.
In the end I had to get a solicitor to photocopy my birth certificate and put a stamp on it to verify that it was a copy of a real document, and that was posted to London someplace along with a complaint.
A few weeks later we got an apology and a little ceramic pig (piggy bank, literally a pig).
So this "computer says no" nonsense is as old as computers. All AI has done is give people more reasons why no.
Icon, because.......
It is not surprising that this company is soaring financially. This is a time when governments everywhere are becoming more and more attuned to the idea of surveillance, due process be damned. Cue V for Vendetta. Honestly, I am starting to believe that that film, as well as Idiocracy, are actual documentaries, not fiction.
If they are looking for a new 'eminence grise', I believe that Peter Mandelson may soon be (un)-available, depending on the Police criminal investigation into his links with a certain Mr J Epstein. He seems willing to work with almost anyone.
Karp's 'philosophising' contained far too much in the way of 'buzzword bingo' for my liking. (OK, admission, I barely understood what he was going on about, just that he was trying to make rich, rightwing, mostly white, mostly men, feel that they are the true 'majority' of Americans.)
Shivers down spines all round.
Reminded me of when Eric Cantona, of Manchester United fame?, started being poetic and philosophical drivel started coming out of his mouth that made no sense, even then and less so now!
https://www.youtube.com/watch?v=TbwV5XX6phU&t=2s
I always took that (*) to be a rather obvious dig at the press chasing after him for a juicy story. Something that seems even more obvious when you see it in context at a press conference, particularly as it was apparently the one that took place after the infamous incident where he drop-kicked and punched a fan shouting abuse from the stands.
As one of the comments on the video notes, he basically insulted them to their face then walked out.
(*) "When the seagulls follow the trawler, it's because they think sardines will be thrown into the sea."
"Palantir declares itself the guardian of Americans' rights" ?
Are these "rights" held in the same database that holds all the other private information of Americans?
Palantir Technologies sells an AI-based platform that allows its users – among them, military and law enforcement agencies – to analyze personal data, including social media profiles, personal information and physical characteristics. These are used to identify and surveil individuals.In March, Trump signed an executive order requiring all agencies and departments of the federal government to share data on Americans. To get the job done, Trump chose Palantir Technologies.
According to New York Times reporting, Palantir’s software may now be used to combine data gleaned from the Department of Homeland Security, the Department of Defense, the Department of Health and Human Services, the Social Security Administration and the Internal Revenue Service. Meanwhile, the administration wants access to citizens’ and others’ bank account numbers and medical claims.
https://www.theguardian.com/commentisfree/2025/jun/30/peter-thiel-palantir-threat-to-americans
Oh, and this would be this Alex Karp:
Karp doesn’t hide his politics. He’s pro-military, anti-transparency and openly contemptuous of Silicon Valley’s squeamishness. While other CEOs flirt with ethics boards and open letters, Karp says the quiet part loud: Palantir is here to wage war—on inefficiency, on bureaucracy, on enemies foreign and domestic.- https://asiatimes.com/2025/05/the-most-dangerous-man-in-america-isnt-trump-its-alex-karp/He ridicules the idea that tech should be restrained by liberal hand-wringing or ethical hesitation. To Karp, the moral compass is obsolete. What matters is effectiveness—disruption, domination, and deployment. He speaks like someone who doesn’t just want to assist power, but to optimize it, weaponize it, and automate it.
'Cos I don't have memorised which one does what, so tried https://constitution.laws.com/4th-amendment, looks like it might be relevant to the quest, as it is supposed to simplify and explain the US Constitution, which sounds about right for this time of the evening.
Nope. It is "temporarily unavailable" in my region (somewhere deep in the UK) for "security reasons", as is the entire site.
Probably(!) nothing at all to do with Palantir, but it feels a wee bit odd to have any "security reasons" for restricting reading about this; is someone worried we'll do something nefarious with the knowledge? Maybe they are worried knowledge of individual US Rights might get back to the wrong people?
At least Wikipedia isn't as guarded. Yet.
Yeah, blocked here in the UK too, and via my Germany server. My USA server worked fine though.
<geeky pedant>They should be using 403 not 503 as the http code. Or maybe 451 (unavailable for legal reasons) but definitely a 4XX not a 5XX</geeky pedant>
laws.com is hugely commercial, and designed for ads. It's possible that ad blocking triggered on it, or the site itself didn't want to serve pages outside the USA. That site is not exactly trustworthy, or even that well known in the US.
As someone who lives in the US, I prefer getting info from the various universities and actual law schools who put some effort into explanation.
The US Congress' Constitution site works fine from here. Fourth Amendment:
"The right of the people to be secure in their persons, houses, papers, and effects, against unreasonable searches and seizures, shall not be violated, and no Warrants shall issue, but upon probable cause, supported by Oath or affirmation, and particularly describing the place to be searched, and the persons or things to be seized."Palantir's totalitarian surveillance everywhere at all times clearly violates that, imho.
I'll just remind people that "laws.com" is a highly commercial site, and is the wrong place to go for this sort of information anyway. Their "About Us" page is very transparent that their purpose is to serve ads to people who visit.
I recommend Cornell's Law school summary and full text, and not something designed primarily to serve ads.
That if they have preemptively already collected every scrap of data on people, they can preserve our 4th amendment rights to search and seizure because what's the point of cops searching and seizing if Palantir has already given the cops access to everything there is to know about you?
> ICE has drawn criticism for its activities in Minnesota over the last month after its agents shot and killed two American citizens while bystanders captured the events on video.
The groups organising the ‘bystanders’ being “ICE Out For Good” / “ICE Out of Everywhere” coalitions, American Civil Liberties Union (ACLU), Voto Latino, United We Dream, Labor unions and labor councils. Finance provided by the “Headwaters Foundation for Justice” (Open Society Foundations). These are the same tactics that manufactured the Black Lives Matter anarchy.
So, they chose to name their company after a tool of evil [*], they created a tool of evil, and now they're trying to convince the world that they're not evil?
Good luck with that.
[*] Tolkien was more subtle. IIUC, his original palantíri (the so-called "seeing stones") weren't created for malign purposes, but had mostly fallen into evil hands by the time Lord of the Rings takes place. Thiel, Karp, et al have simply skipped over that and gotten straight to the point.
So, they chose to name their company after a tool of evil [*], they created a tool of evil, and now they're trying to convince the world that they're not evil?
I noticed that, the first time I saw anything about them. First I was mad that an evil company had named themself with a LotR name, but then I thought, wait, do they know what the Palantiri were?
" ... every institution that uses our product is doing it within conformity of the law and the ethics of America,"
Ok, so
1. America has ethics?
2. This is the Freudianist of slips.... other countries have their own ideas around ethics, and also laws. Does the UK subscribe to American ethics such that buying palantir is fine? Answer = no. American laws? Double no.
Is it better to suffer with palantir all over (NHS, MoD etc) or presumably have less functional but safer / homegrown products? It is a question that isn't easily answered.
"Palantir declares itself the guardian of Americans' rights"
The same way Stasi was guarding the rights of people in East Germany. And that is not a joke: Palantir does the same thing, but a lot more automated way.
If anyone believes it will not be used against 'enemies of state', i.e. Trump/Republicans, they're dangerously naive.
Trump and DHS have already marked opposion as "terrorists" and Palantir offers tools for 'containing' terrorism. i.e. killing them all.
ICE is already using "services" from Palantir heavily, targeting opposition and 'leaders', whoever they may be, and then killing them. Not an accident, but planned murder.