I’ve talked on Techdirt about just a few of my AI-related experiments over the past few years, including how I use it to help me edit pieces, which I still write myself. I still have no intention of letting AI write for me, but as the underlying technology has continued to level up, every so often I’ll run a test to see if it could write a better Techdirt post than I can. I don’t think it’s there (and I’m still not convinced it will ever get there), but I figured I can share the process with you, and let you be the judge.

I wanted to pick a fairly straightforward article, rather than a more complex one, just to see how well it works. In this case, I figured I’d try it with the story I published last week about Judge Boasberg ruling against the Trump administration and calling out how the DOJ barely participated in the case, and effectively told him to “pound sand” (a quote directly from the judge).

I know that just telling it to write a Techdirt article by itself will lead to pretty bland “meh” content. So before I even get to the prompt, there are some steps I need to include. First, over time I continue to adjust the underlying “system prompt” I use for editing my pieces. I won’t post the entire system prompt here as it’s not that interesting, but I do use it to make it clear its job is to help me be a better writer, not to be a sycophant, not to try to change things just for the sake of change, and to suggest things that will most help the reader.

I also have a few notes in it about avoiding recommending certain “AI-style” cliches like “it’s not this, it’s that.” Also, a specific one for me: “don’t suggest changing ‘fucked up’ to ‘messed up.’” It does that a lot for my writing.

But that’s not all. I also feed in Techdirt samples, which are a collection of ten of my favorite articles, so it gets a sense of what a “Techdirt article” looks like. On top of that, I give it a “Masnick Style Guide” that I had created after feeding a bunch of Techdirt articles into three different LLMs, asking for each to produce a style guide, and then having NotebookLLM combine them all into a giant “Masnick style-guide.”

Then, I feed it any links, including earlier stories on Techdirt, that are relevant, before finally writing out a prompt that can be pretty long. In this test case, I fed it the PDF file of the decision. I also gave it Techdirt’s previous stories about Judge Boasberg.

Finally, I gave it a starting prompt with a fair bit of explanation of what angle I was hoping to see a Techdirt post on this topic. So here’s my full prompt:

Can you write a Techdirt style first draft of a post (see the attached Techdirt post samples, as well as the even more important Masnick style guide, which you should follow) about the attached ruling in the JGG v. Trump case by Judge James Boasberg. I have also attached a page of previous articles about Judge Boasberg which you should consider, especially as some reference this same case.

You may also want to highlight that Judge Boasberg just was vindicated after the DOJ filed a vexatious complaint against him because of earlier rulings in this case, but that complaint has been easily dismissed. The crux of this article, though, should be on the very strong language Boasberg uses, including the astoundingly candid statement that he felt the government “apparently was no interested in participating in this process” and how he read their response as telling “the Court to pound sand.” There are other parts of the ruling that are useful as well. It should also call out the specific remedy here, and how weak it feels, given the situation explained in the ruling and the DOJ’s actions. Yes, they lost the case, but this still feels like a slap on the wrist with no real consequences for the DOJ.

As always with Techdirt posts, instead of doing in-line quotes, we usually do blockquotes, often of one or even multiple paragraphs from the original sources, so please adhere to that style. Take all of this info and draft the best Techdirt post you can regarding the topic.

And… you can see the results embedded below. I’ve also embedded my original article (though you can just go read it on the site directly). I’m amused that it added a “from the such and such dept” line as well as tags, both of which are core parts of Techdirt posts, but not things I asked it for.

I’m extremely biased, as this is a question of who writes better, me or the machine, and I still think I’m better than the machine. But, I also have to admit it’s not bad. It’s decent. If I had that submitted by another writer, there are definitely changes and edits I’d make, especially to the crappy cliche’d ending. But it’s way better than what most people think of as traditional ChatGPT output, in part because of all the context and detailed instructions I fed it.

Just for fun, I then also asked my editing tool to do its own edit on its own writing (usually not a good idea to let it grade its own homework), but here’s what it had to say:

solid draft. the “pound sand” framing works well and the frustration comes through. few things:

the tension setup: you flag “frustratingly toothless” in graf 3 then say “on one level this is a win” much later. that’s the right editorial instinct—there IS genuine tension here—but you’re burying the lede on your own argument. consider setting up that complexity earlier so readers know they’re getting nuance, not whiplash.

missing a key detail from the ruling: Boasberg notes that “even Plaintiffs’ counsel could not represent how many of the 137 are still in Venezuela and how many wish to proceed with habeas.” that’s devastating. the chaos is so complete that the lawyers literally don’t know where everyone is. worth including.

the numbered remedies block: you cut it off mid-list. the 5th point actually matters—there’s a March 13 deadline for the government to file a Status Report explaining how/when they’ll transport people back. that’s your next milestone. either include it or acknowledge you’re excerpting.

the Venezuela carve-out: you mention it but undersell it. the ruling specifically says it’s “mindful” of the “situation in Venezuela remains in flux” given “the United States’s recent law-enforcement action there.” that’s pretty ominous language from a federal judge about whatever the hell the administration is doing in Venezuela right now. might be worth a parenthetical noting this deserves its own article.

the closer: “I wouldn’t hold my breath” is fine but feels like boilerplate. you’ve got stronger material to end on—maybe the March 13 deadline, or something that points forward rather than just shrugging.

one small thing: “a complaint that was summarily dismissed” in graf 2—might want “recently dismissed” or similar since it was just last week. “summarily” suggests procedure when really the story is how embarrassing the dismissal was.

overall structure is good. the piece does what Techdirt does well: walks through the actual document, quotes liberally, and doesn’t pretend the “win” is bigger than it is.

You’ll note that it also calls out its own weak ending, just like I did. It is kind of wild to see the AI call out its own weaknesses, while making you wonder—if that’s the case—why did it not catch those earlier and fix them? And that then makes you wonder if it’s just coming up with a critique for the sake of giving one (though, that ending really is weak).

The other thing I’ll note is, again, this actually was still a fair bit of work. It was less than writing the whole thing myself, but even just writing out the prompt itself took time, and this piece would still need a fair bit of editing anyway for publication which would probably take away any time benefit.

Overall, though, you can see how the technology is certainly getting better. I still don’t think it can write as well as I do, but there are some pretty good bits in there.

Once again, this tech remains quite useful as a tool to assist people with their work. But it’s not really good at replacing your work. Indeed, if I asked the AI to write articles for Techdirt, I’d probably spend just as much time rewriting/fixing it as I would just writing the original in the first place. It still provides me very good feedback (on this article that you’re reading now, for example, the AI editor warned me that my original ending was pretty weak, and suggested I add a paragraph talking more about the conclusions which, uh, is what I’m now doing here).

I honestly think the biggest struggle with AI over the next year or so is going to be between the people who insist it can totally replace humans, leading to shoddy and problematic work, and the smaller group of people who use it as a tool to assist them in doing their own work better. The problems come in when people overestimate its ability to do the former, while underestimating its ability to do the latter.

Surveillance technology vendors, federal agencies, and wealthy private donors have long helped provide local law enforcement “free” access to surveillance equipment that bypasses local oversight. The result is predictable: serious accountability gaps and data pipelines to other entities, including Immigration and Customs Enforcement (ICE), that expose millions of people to harm.

The cost of “free” surveillance tools — like automated license plate readers (ALPRs), networked cameras, face recognition, drones, and data aggregation and analysis platforms — is measured not in tax dollars, but in the erosion of civil liberties. 

The collection and sharing of our data quietly generates detailed records of people’s movements and associations that can be exposed, hacked, or repurposed without their knowledge or consent. Those records weaken sanctuary and First Amendment protections while facilitating the targeting of vulnerable people.   

Cities can and should use their power to reject federal grants, vendor trials, donations from wealthy individuals, or participation in partnerships that facilitate surveillance and experimentation with spy tech. 

If these projects are greenlit, oversight is imperative. Mechanisms like public hearings, competitive bidding, public records transparency, and city council supervision aid to ensure these acquisitions include basic safeguards — like use policies, audits, and consequences for misuse — to protect the public from abuse and from creeping contracts that grow into whole suites of products. 

Clear policies and oversight mechanisms must be in place before using any surveillance tools, free or not, and communities and their elected officials must be at the center of every decision about whether to bring these tools in at all.

Here are some of the most common methods “free” surveillance tech makes its way into communities.

Trials and Pilots

Police departments are regularly offered free access to surveillance tools and software through trials and pilot programs that often aren’t accompanied by appropriate use policies. In many jurisdictions, trials do not trigger the same requirements to go before decision-makers outside the police department. This means the public may have no idea that a pilot program for surveillance technology is happening in their city. 

In Denver, Colorado, the police department is running trials of possible unmanned aerial vehicles (UAVs) for a drone-as-first-responder (DFR) program from two competing drone vendors: Flock Safety Aerodome drones (through August 2026) and drones from the company Skydio, partnering with Axon, the multi-billion dollar police technology company behind tools like Tasers and AI-generated police reports. Drones create unique issues given their vantage for capturing private property and unsuspecting civilians, as well as their capacity to make other technologies, like ALPRs, airborne. 

Functional, Even Without Funding 

We’ve seen cities decide not to fund a tool, or run out of funding for it, only to have a company continue providing it in the hope that money will turn up. This happened in Fall River, Massachusetts, where the police department decided not to fund ShotSpotter’s $90,000 annual cost and its frequent false alarms, but continued using the system when the company provided free access. 

In May 2025, Denver’s city council unanimously rejected a $666,000 contract extension for Flock Safety ALPR cameras after weeks of public outcry over mass surveillance data sharing with federal immigration enforcement. But Mayor Mike Johnston’s office allowed the cameras to keep running through a “task force” review, effectively extending the program even after the contract was voted down. In response, the Denver Taskforce to Reimagine Policing and Public Safety and Transforming Our Communities Alliance launched a grassroots campaign demanding the city “turn Flock cameras off now,” a reminder that when surveillance starts as a pilot or time‑limited contract, communities often have to fight not just to block renewals but to shut the systems off.

 Importantly, police technology companies are developing more features and subscription-based models, so what’s “free” today frequently results in taxpayers footing the bill later. 

Gifts from Police Foundations and Wealthy Donors

Police foundations and the wealthy have pushed surveillance-driven agendas in their local communities by donating equipment and making large monetary gifts, another means of acquiring these tools without public oversight or buy-in.

In Atlanta, the Atlanta Police Foundation (APF) attempted to use its position as a private entity to circumvent transparency. Following a court challenge from the Atlanta Community Press Collective and Lucy Parsons Labs, a Georgia court determined that the APF must comply with public records laws related to some of its actions and purchases on behalf of law enforcement.
In San Francisco, billionaire Chris Larsen has financially supported a supercharging of the city’s surveillance infrastructure, donating $9.4 million to fund the San Francisco Police Department’s (SFPD) Real-Time Investigation Center, where a menu of surveillance technologies and data come together to surveil the city’s residents. This move comes after the billionaire backed a ballot measure, which passed in March 2025, eroding the city’s surveillance technology law and allowing the SFPD free rein to use new surveillance technologies for a full year without oversight.

Free Tech for Federal Data Pipelines

Federal grants and Department of Homeland Security funding are another way surveillance technology appears free to, only to lock municipalities into long‑term data‑sharing and recurring costs. 

Through the Homeland Security Grant Program, which includes the State Homeland Security Program (SHSP) and the Urban Areas Security (UASI) Initiative, and Department of Justice programs like Byrne JAG, the federal government reimburses states and cities for “homeland security” equipment and software, including including law‑enforcement surveillance tools, analytics platforms, and real‑time crime centers. Grant guidance and vendor marketing materials make clear that these funds can be used for automated license plate readers, integrated video surveillance and analytics systems, and centralized command‑center software—in other words, purchases framed as counterterrorism investments but deployed in everyday policing.

Vendors have learned to design products around this federal money, pitching ALPR networks, camera systems, and analytic platforms as “grant-ready” solutions that can be acquired with little or no upfront local cost. Motorola Solutions, for example, advertises how SHSP and UASI dollars can be used for “law enforcement surveillance equipment” and “video surveillance, warning, and access control” systems. Flock Safety, partnering with Lexipol, a company that writes use policies for law enforcement, offers a “License Plate Readers Grant Assistance Program” that helps police departments identify federal and state grants and tailor their applications to fund ALPR projects. 

Grant assistance programs let police chiefs fast‑track new surveillance: the paperwork is outsourced, the grant eats the upfront cost, and even when there is a formal paper trail, the practical checks from residents, councils, and procurement rules often get watered down or bypassed.

On paper, these systems arrive “for free” through a federal grant; in practice, they lock cities into recurring software, subscription, and data‑hosting fees that quietly turn into permanent budget lines—and a lasting surveillance infrastructure—as soon as police and prosecutors start to rely on them. In Santa Cruz, California, the police department explicitly sought to use a DHS-funded SHSP grant to pay for a new citywide network of Flock ALPR cameras at the city’s entrances and exits, with local funds covering additional cameras. In Sumner, Washington, a $50,000 grant was used to cover the entire first year of a Flock system — including installation and maintenance — after which the city is on the hook for roughly $39,000 every year in ongoing fees. The free grant money opens the door, but local governments are left with years of financial, political, and permanent surveillance entanglements they never fully vetted.

The most dangerous cost of this “free” funding is not just budgetary; it is the way it ties local systems into federal data pipelines. Since 9/11, DHS has used these grant streams to build a nationwide network of at least 79–80 state and regional fusion centers that integrate and share data from federal, state, local, tribal, and private partners. Research shows that state fusion centers rely heavily on the DHS Homeland Security Grant Program (especially SHSP and UASI) to “mature their capabilities,” with some centers reporting that 100 percent of their annual expenditures are covered by these grants. 

Civil rights investigations have documented how this funding architecture creates a backdoor channel for ICE and other federal agencies to access local surveillance data for their own purposes. A recent report by the Surveillance Technology Oversight Project (S.T.O.P.) describes ICE agents using a Philadelphia‑area fusion center to query the city’s ALPR network to track undocumented drivers in a self‑described sanctuary city.

Ultimately, federal grants follow the same script as trials and foundation gifts: what looks “free” ends up costing communities their data, their sanctuary protections, and their power over how local surveillance is used.

Protecting Yourself Against “Free” Technology

The most important protection against “free” surveillance technology is to reject it outright. Cities do not have to accept federal grants, vendor trials, or philanthropic donations. Saying no to “free” tech is not just a policy choice; it is a political power that local governments possess and can exercise. Communities and their elected officials can and should refuse surveillance systems that arrive through federal grants, vendor pilots, or private donations, regardless of how attractive the initial price tag appears. 

For those cities that have already accepted surveillance technology, the imperative is equally clear: shut it down. When a community has rejected use of a spying tool, the capabilities, equipment, and data collected from that tool should be shut off immediately. Full stop.

And for any surveillance technology that remains in operation, even temporarily, there must be clear rules: when and how equipment is used, how that data is retained and shared, who owns data and how companies can access and use it, transparency requirements, and consequences for any misuse and abuse. 

“Free” surveillance technology is never free. Someone profits or gains power from it. Police technology vendors, federal agencies, and wealthy donors do not offer these systems out of generosity; they offer them because surveillance serves their interests, not ours. That is the real cost of “free” surveillance.

Originally posted to EFF’s Deeplinks blog.

Dr. Vinay Prasad is currently the FDA’s top vaccine regulator. He’s also one of many medical goons hand-picked by RFK Jr. to help lead his decidedly anti-vaxxer movement. In fact, the last time we discussed Prasad, it was over his selective censorship attempts at avoiding public criticism for his anti-vaxxer nonsense. If you show clips of Prasad spewing his anti-vaxxer views to critique them, he’ll have your YouTube channel axed. If you show those same clips to praise his nonsense, you get to continue on unmolested.

He’s an asshat, in other words. An anti-science, anti-medicine asshat. And he’s also someone who is unilaterally keeping us from making progress on vaccines, apparently out of pure joy in exercising such power.

Moderna is producing a new influenza vaccine, this one utilizing mRNA technology, a la the COVID vaccine. Moderna sent an application to the FDA for a review of the vaccine it has produced, as well as the data from the trials the company conducted to demonstrate its efficacy. We learned last week that the FDA flatly refused to review any of this data.

In a news release late Tuesday, Moderna said it was blindsided by the FDA’s refusal, which the FDA cited as being due to the design of the company’s Phase 3 trial for its mRNA flu vaccine, dubbed mRNA-1010. Specifically, the FDA’s rejection was over the comparator vaccine Moderna used.

In the trial, which enrolled nearly 41,000 participants and cost hundreds of millions of dollars, Moderna compared the safety and efficacy of mRNA-1010 to licensed standard-dose influenza vaccines, including Fluarix, made by GlaxoSmithKline. The trial found that mRNA-1010 was superior to the comparators.

Moderna said the FDA reviewed and accepted its trial design on at least two occasions (in April 2024 and again in August 2025) before it applied for approval of mRNA-1010. It also noted that Fluarix has been used as a comparator vaccine in previous flu vaccine trials, which tested vaccines that went on to earn approval.

This looks for all the world like Moderna did what it was supposed to do in getting the proper sign-offs from the FDA to conduct its trials. Prasad himself sent the refusal notice to Moderna, however, and cited within it that the trials Moderna conducted, which were signed off on by the FDA, were not appropriate. The letter didn’t bother to indicate why.

But in a letter dated February 3, Vinay Prasad, the FDA’s top vaccine regulator under the Trump administration, informed Moderna that the agency does not consider the trial “adequate and well-controlled” because the comparator vaccine “does not reflect the best-available standard of care.”

In its news release, Moderna noted that neither the FDA’s regulation nor its guidance to industry makes any reference to a requirement of the “best-available standard of care” in comparators.

Everyone at Moderna was understandably confused. The company has already reached out asking to meet with the FDA, ostensibly to sit down in a conference room with them, look them in the eye, and ask “wut?”.

The answer is unlikely to be satisfying. And it should be quite alarming to the rest of us. That’s because the rejection of a review of all of this data reportedly came from Prasad and Prasad alone, over the objections of his own scientists at the FDA.

Vinay Prasad, the Trump administration’s top vaccine regulator at the Food and Drug Administration, single-handedly decided to refuse to review Moderna’s mRNA flu vaccine, overruling agency scientists, according to reports from Stat News and The Wall Street Journal.

Stat was first to report, based on unnamed FDA sources, that a team of career scientists at the agency was ready to review the vaccine and that David Kaslow, a top career official who reviews vaccines, even wrote a memo objecting to Prasad’s rejection. The memo reportedly included a detailed explanation of why the review should proceed.

According to those same sources, Prasad’s reason for refusing to review Moderna’s vaccine makes little sense. The story goes like this. As Moderna was seeking guidance for its trials for the vaccine, it chose a currently licensed flu vaccine against which to compare its own vaccine. At one point, the FDA suggested a different comparative vaccine be used. Moderna declined that suggestion and moved forward with the comparative vaccine it originally chose. Despite that difference the FDA reviewed the company’s plans for its trial on several occasions and at no point suggested its choices were a show-stopper.

That’s it. That’s the whole thing. Prasad is claiming that the choice Moderna made for a comparative vaccine, for which the company received only mild feedback from the FDA, is why the FDA is refusing to review this mRNA flu vaccine entirely.

Because that reasoning is almost certainly bullshit. As evidence of that, these same sources from within the FDA offered up this:

This wasn’t enough for Prasad, who, according to the Journal’s sources, told FDA staff that he wants to send more such refusal letters that appear to blindside drug developers. The review staff apparently pushed back, noting that such moves break with the agency’s practices and could open it up to being sued. Prasad reportedly dismissed concern over possible litigation. Trump’s FDA Commissioner Marty Makary seemed similarly unconcerned, suggesting on Fox News that Moderna’s trial may be “unethical.”

The explanation here is remarkably simple. This current government is being run by anti-vaxxers. And these anti-vaxxers are particularly anti-vaxxer-y about mRNA vaccines. And so folks like Prasad are throwing up every roadblock they can dream up to make it as difficult as possible to get new vaccines utilizing new technology approved. Or, as in this case, even reviewed.

Now, if that reads like the opposite of scientific progress to you, give yourself a gold star, because you’re right. Thomas Jefferson once said “I tremble for my country when I reflect that God is just” when, hypocritically, discussing slavery in America. I think we should tremble for our country as well when I reflect that we are getting sicker as a nation, given that we have morons at the helm of the nation’s health.