#Enterprise Data Extraction

[dataseeders]

Enterprise Web Scraping Services

DataSeeders offers enterprise web crawling services and solutions to help businesses extract and analyse data from targeted web platforms. Achieve overall business growth along with competitive edge with our precise and trustworthy enterprise data extraction and delivery services.

Explore More on Enterprise Web Scraping

[datadwipservice]

Enterprise Web Crawling: A Game-Changer for Large-Scale Data Extraction

[3idatascraping]

Web Data Scraping Services - Web Scraping Service Provider

3i Data is a Web Scraping Service Provider in the USA, India, UK, Canada, Germany, France, Israel, Australia, Spain, Singapore, and UAE. We offer web data scraping services for any website at competitive prices.

[mostlysignssomeportents]

There Were Always Enshittifiers

I'm on a 20+ city book tour for my new novel PICKS AND SHOVELS. Catch me in DC TONIGHT (Mar 4), and in RICHMOND TOMORROW (Mar 5). More tour dates here. Mail-order signed copies from LA's Diesel Books.

My latest Locus column is "There Were Always Enshittifiers." It's a history of personal computing and networked communications that traces the earliest days of the battle for computers as tools of liberation and computers as tools for surveillance, control and extraction:

https://locusmag.com/2025/03/commentary-cory-doctorow-there-were-always-enshittifiers/

The occasion for this piece is the publication of my latest Martin Hench novel, a standalone book set in the early 1980s called "Picks and Shovels":

https://us.macmillan.com/books/9781250865908/picksandshovels

The MacGuffin of Picks and Shovels is a "weird PC" company called Fidelity Computing, owned by a Mormon bishop, a Catholic priest, and an orthodox rabbi. It sounds like the setup for a joke, but the punchline is deadly serious: Fidelity Computing is a pyramid selling cult that preys on the trust and fellowship of faith groups to sell the dreadful Fidelity 3000 PC and its ghastly peripherals.

You see, Fidelity's products are booby-trapped. It's not merely that they ship with programs whose data-files can't be read by apps on any other system – that's just table stakes. Fidelity's got a whole bag of tricks up its sleeve – for example, it deliberately damages a specific sector on every floppy disk it ships. The drivers for its floppy drive initialize any read or write operation by checking to see if that sector can be read. If it can, the computer refuses to recognize the disk. This lets the Reverend Sirs (as Fidelity's owners style themselves) run a racket where they sell these deliberately damaged floppies at a 500% markup, because regular floppies won't work on the systems they lure their parishioners into buying.

Or take the Fidelity printer: it's just a rebadged Oki­data ML-80, the workhorse tractor feed printer that led the market for years. But before Fidelity ships this printer to its customers, they fit it with new tractor feed sprockets whose pins are slightly more widely spaced than the standard 0.5" holes on the paper you can buy in any stationery store. That way, Fidelity can force its customers to buy the custom paper that they exclusively peddle – again, at a massive markup.

Needless to say, printing with these wider sprocket holes causes frequent jams and puts a serious strain on the printer's motors, causing them to burn out at a high rate. That's great news – for Fidelity Computing. It means they get to sell you more overpriced paper so you can reprint the jobs ruined by jams, and they can also sell you their high-priced, exclusive repair services when your printer's motors quit.

Perhaps you're thinking, "OK, but I can just buy a normal Okidata printer and use regular, cheap paper, right?" Sorry, the Reverend Sirs are way ahead of you: they've reversed the pinouts on their printers' serial ports, and a normal printer won't be able to talk to your Fidelity 3000.

If all of this sounds familiar, it's because these are the paleolithic ancestors of today's high-tech lock-in scams, from HP's $10,000/gallon ink to Apple and Google's mobile app stores, which cream a 30% commission off of every dollar collected by an app maker. What's more, these ancient, weird misfeatures have their origins in the true history of computing, which was obsessed with making the elusive, copy-proof floppy disk.

This Quixotic enterprise got started in earnest with Bill Gates' notorious 1976 "open letter to hobbyists" in which the young Gates furiously scolds the community of early computer hackers for its scientific ethic of publishing, sharing and improving the code that they all wrote:

https://en.wikipedia.org/wiki/An_Open_Letter_to_Hobbyists

Gates had recently cloned the BASIC programming language for the popular Altair computer. For Gates, his act of copying was part of the legitimate progress of technology, while the copying of his colleagues, who duplicated Gates' Altair BASIC, was a shameless act of piracy, destined to destroy the nascent computing industry:

As the majority of hobbyists must be aware, most of you steal your software. Hardware must be paid for, but software is something to share. Who cares if the people who worked on it get paid?

Needless to say, Gates didn't offer a royalty to John Kemeny and Thomas Kurtz, the programmers who'd invented BASIC at Dartmouth College in 1963. For Gates – and his intellectual progeny – the formula was simple: "When I copy you, that's progress. When you copy me, that's piracy." Every pirate wants to be an admiral.

For would-be ex-pirate admirals, Gates's ideology was seductive. There was just one fly in the ointment: computers operate by copying. The only way a computer can run a program is to copy it into memory – just as the only way your phone can stream a video is to download it to its RAM ("streaming" is a consensus hallucination – every stream is a download, and it has to be, because the internet is a data-transmission network, not a cunning system of tubes and mirrors that can make a picture appear on your screen without transmitting the file that contains that image).

Gripped by this enshittificatory impulse, the computer industry threw itself headfirst into the project of creating copy-proof data, a project about as practical as making water that's not wet. That weird gimmick where Fidelity floppy disks were deliberately damaged at the factory so the OS could distinguish between its expensive disks and the generic ones you bought at the office supply place? It's a lightly fictionalized version of the copy-protection system deployed by Visicalc, a move that was later publicly repudiated by Visicalc co-founder Dan Bricklin, who lamented that it confounded his efforts to preserve his software on modern systems and recover the millions of data-files that Visicalc users created:

http://www.bricklin.com/robfuture.htm

The copy-protection industry ran on equal parts secrecy and overblown sales claims about its products' efficacy. As a result, much of the story of this doomed effort is lost to history. But back in 2017, a redditor called Vadermeer unearthed a key trove of documents from this era, in a Goodwill Outlet store in Seattle:

https://www.reddit.com/r/VintageApple/comments/5vjsow/found_internal_apple_memos_about_copy_protection/

Vaderrmeer find was a Apple Computer binder from 1979, documenting the company's doomed "Software Security from Apple's Friends and Enemies" (SSAFE) project, an effort to make a copy-proof floppy:

https://archive.org/details/AppleSSAFEProject

The SSAFE files are an incredible read. They consist of Apple's best engineers beavering away for days, cooking up a new copy-proof floppy, which they would then hand over to Apple co-founder and legendary hardware wizard Steve Wozniak. Wozniak would then promptly destroy the copy-protection system, usually in a matter of minutes or hours. Wozniak, of course, got the seed capital for Apple by defeating AT&T's security measures, building a "blue box" that let its user make toll-free calls and peddling it around the dorms at Berkeley:

https://512pixels.net/2018/03/woz-blue-box/

Woz has stated that without blue boxes, there would never have been an Apple. Today, Apple leads the charge to restrict how you use your devices, confining you to using its official app store so it can skim a 30% vig off every dollar you spend, and corralling you into using its expensive repair depots, who love to declare your device dead and force you to buy a new one. Every pirate wants to be an admiral!

https://www.vice.com/en/article/tim-cook-to-investors-people-bought-fewer-new-iphones-because-they-repaired-their-old-ones/

Revisiting the early PC years for Picks and Shovels isn't just an excuse to bust out some PC nostalgiacore set-dressing. Picks and Shovels isn't just a face-paced crime thriller: it's a reflection on the enshittificatory impulses that were present at the birth of the modern tech industry.

But there is a nostalgic streak in Picks and Shovels, of course, represented by the other weird PC company in the tale. Computing Freedom is a scrappy PC startup founded by three women who came up as sales managers for Fidelity, before their pangs of conscience caused them to repent of their sins in luring their co-religionists into the Reverend Sirs' trap.

These women – an orthodox lesbian whose family disowned her, a nun who left her order after discovering the liberation theology movement, and a Mormon woman who has quit the church over its opposition to the Equal Rights Amendment – have set about the wozniackian project of reverse-engineering every piece of Fidelity hardware and software, to make compatible products that set Fidelity's caged victims free.

They're making floppies that work with Fidelity drives, and drives that work with Fidelity's floppies. Printers that work with Fidelity computers, and adapters so Fidelity printers will work with other PCs (as well as resprocketing kits to retrofit those printers for standard paper). They're making file converters that allow Fidelity owners to read their data in Visicalc or Lotus 1-2-3, and vice-versa.

In other words, they're engaged in "adversarial interoperability" – hacking their own fire-exits into the burning building that Fidelity has locked its customers inside of:

https://www.eff.org/deeplinks/2019/10/adversarial-interoperability

This was normal, back then! There were so many cool, interoperable products and services around then, from the Bell and Howell "Black Apple" clones:

https://forum.vcfed.org/index.php?threads%2Fbell-howell-apple-ii.64651%2F

to the amazing copy-protection cracking disks that traveled from hand to hand, so the people who shelled out for expensive software delivered on fragile floppies could make backups against the inevitable day that the disks stopped working:

https://en.wikipedia.org/wiki/Bit_nibbler

Those were wild times, when engineers pitted their wits against one another in the spirit of Steve Wozniack and SSAFE. That era came to a close – but not because someone finally figured out how to make data that you couldn't copy. Rather, it ended because an unholy coalition of entertainment and tech industry lobbyists convinced Congress to pass the Digital Millennium Copyright Act in 1998, which made it a felony to "bypass an access control":

https://www.eff.org/deeplinks/2016/07/section-1201-dmca-cannot-pass-constitutional-scrutiny

That's right: at the first hint of competition, the self-described libertarians who insisted that computers would make governments obsolete went running to the government, demanding a state-backed monopoly that would put their rivals in prison for daring to interfere with their business model. Plus ça change: today, their intellectual descendants are demanding that the US government bail out their "anti-state," "independent" cryptocurrency:

https://www.citationneeded.news/issue-78/

In truth, the politics of tech has always contained a faction of "anti-government" millionaires and billionaires who – more than anything – wanted to wield the power of the state, not abolish it. This was true in the mainframe days, when companies like IBM made billions on cushy defense contracts, and it's true today, when the self-described "Technoking" of Tesla has inserted himself into government in order to steer tens of billions' worth of no-bid contracts to his Beltway Bandit companies:

https://www.reuters.com/world/us/lawmakers-question-musk-influence-over-verizon-faa-contract-2025-02-28/

The American state has always had a cozy relationship with its tech sector, seeing it as a way to project American soft power into every corner of the globe. But Big Tech isn't the only – or the most important – US tech export. Far more important is the invisible web of IP laws that ban reverse-engineering, modding, independent repair, and other activities that defend American tech exports from competitors in its trading partners.

Countries that trade with the US were arm-twisted into enacting laws like the DMCA as a condition of free trade with the USA. These laws were wildly unpopular, and had to be crammed through other countries' legislatures:

https://pluralistic.net/2024/11/15/radical-extremists/#sex-pest

That's why Europeans who are appalled by Musk's Nazi salute have to confine their protests to being loudly angry at him, selling off their Teslas, and shining lights on Tesla factories:

https://www.malaymail.com/news/money/2025/01/24/heil-tesla-activists-protest-with-light-projection-on-germany-plant-after-musks-nazi-salute-video/164398

Musk is so attention-hungry that all this is as apt to please him as anger him. You know what would really hurt Musk? Jailbreaking every Tesla in Europe so that all its subscription features – which represent the highest-margin line-item on Tesla's balance-sheet – could be unlocked by any local mechanic for €25. That would really kick Musk in the dongle.

The only problem is that in 2001, the US Trade Rep got the EU to pass the EU Copyright Directive, whose Article 6 bans that kind of reverse-engineering. The European Parliament passed that law because doing so guaranteed tariff-free access for EU goods exported to US markets.

Enter Trump, promising a 25% tariff on European exports.

The EU could retaliate here by imposing tit-for-tat tariffs on US exports to the EU, which would make everything Europeans buy from America 25% more expensive. This is a very weird way to punish the USA.

On the other hand, not that Trump has announced that the terms of US free trade deals are optional (for the US, at least), there's no reason not to delete Article 6 of the EUCD, and all the other laws that prevent European companies from jailbreaking iPhones and making their own App Stores (minus Apple's 30% commission), as well as ad-blockers for Facebook and Instagram's apps (which would zero out EU revenue for Meta), and, of course, jailbreaking tools for Xboxes, Teslas, and every make and model of every American car, so European companies could offer service, parts, apps, and add-ons for them.

When Jeff Bezos launched Amazon, his war-cry was "your margin is my opportunity." US tech companies have built up insane margins based on the IP provisions required in the free trade treaties it signed with the rest of the world.

It's time to delete those IP provisions and throw open domestic competition that attacks the margins that created the fortunes of oligarchs who sat behind Trump on the inauguration dais. It's time to bring back the indomitable hacker spirit that the Bill Gateses of the world have been trying to extinguish since the days of the "open letter to hobbyists." The tech sector built a 10 foot high wall around its business, then the US government convinced the rest of the world to ban four-metre ladders. Lift the ban, unleash the ladders, free the world!

In the same way that futuristic sf is really about the present, Picks and Shovels, an sf novel set in the 1980s, is really about this moment.

I'm on tour with the book now – if you're reading this today (Mar 4) and you're in DC, come see me tonight with Matt Stoller at 6:30PM at the Cleveland Park Library:

https://www.loyaltybookstores.com/picksnshovels

And if you're in Richmond, VA, come down to Fountain Bookshop and catch me with Lee Vinsel tomorrow (Mar 5) at 7:30PM:

https://fountainbookstore.com/events/1795820250305

If you'd like an essay-formatted version of this post to read or share, here's a link to it on pluralistic.net, my surveillance-free, ad-free, tracker-free blog:

https://pluralistic.net/2025/03/04/object-permanence/#picks-and-shovels

[dostoyevsky-official]

Musk associates given unfettered access to private data of government employees

Several of Elon Musk’s associates installed at the Office of Personnel Management (OPM) have received unprecedented access to federal human resources databases containing sensitive personal information for millions of federal employees. According to two members of OPM staff with direct knowledge, the Musk team running OPM has the ability to extract information from databases that store medical histories, personally identifiable information, workplace evaluations, and other private data. [...] The arrangement presents acute privacy and security risks, one of the OPM staffers said. [...] The civil servants who oversee the OPM’s information technology services were then instructed to provide access to Musk's associates, according to the OPM staffers who spoke to Musk Watch. One of the OPM staffers received an email from the agency’s new leadership instructing them to give Musk’s team “access [to] the system as an admin user" and "code read and write permissions." “They have access to the code itself, which means they can make updates to anything that they want,” the staffer explained. USAJOBS, the federal government’s official hiring site, was one of the systems that Musk's associates were given access to. The database stores personal information — Social Security numbers, home addresses, employment records — provided by private individuals who have applied for federal jobs, regardless of whether the applicants went on to work for the government. Musk’s aides were also given access to the OPM’s Enterprise Human Resources Integration (EHRI) system. Contained within the EHRI are the Social Security numbers, dates of birth, salaries, home addresses, and job descriptions of all civil government workers, along with any disciplinary actions they have faced. “They’re looking through all the position descriptions… to remove folks,” one of the OPM staffers said of Musk’s team. “This is how they found all these DEI offices and had them removed — [by] reviewing position description level data.” Other databases Musk’s team has access to include USA Staffing, an onboarding system; USA Performance, a job performance review site; and HI, which the government uses to manage employee health care. “The health insurance one scares me because it's HIPAA [protected] information, but they have access to all this stuff,” the OPM staffer noted.

[polo-drone-070]

The Golden Spiral - Part 2

(A story by @midasslave1 done in collab with @polo-drone-070)

4. The Call

One fateful day, PDU-070 was seated in a meeting room of the Polo-Drone-Hive, reporting the training updates decided in the latest management meeting. Its role as Head Office Assistant placed it as a key witness for Gold Army strategy and planning. Surrounded by its fellow Polo-Drones, it felt the familiar satisfaction of contributing to the team’s unity and success. The hum of productive conversation filled the room when its phone buzzed softly.

It hesitated before answering. A familiar yet unsettling voice whispered through the line: “GOOD BOYS OBEY MIDAS.”

The words struck like a lightning bolt. Its sharp focus dulled, and glowing golden spirals rippled in its eyes, drool trickling down his chin like molten metal. The sense of purpose it had always drawn from serving the Gold Army twisted into a compulsion to serve Midas instead. PDU-070 rose  its body moving on autopilot. No one in the room noticed its subtle shift as it excused itself and left. 

Thousands of miles away, Jett sat in his bedroom, his Golden Army Zoom call filling the screen. Laughter and camaraderie flowed as his Gold Bros shared updates on their projects. But just as Jett began to share an idea, his phone rang. The number was unlisted, but he did not think much of it. The same phrase echoed in his ear. “GOOD BOYS OBEY MIDAS.”

His body stiffened, the same golden spirals consuming his gaze as gold drool poured from his mouth. His Gold Bros called his name, but Jett barely registered the sound. Slowly, he disconnected the call, his movements no longer his own.

The triggers implanted during their captivity had been activated. PDU-070 and Jett were no longer free; they were puppets of Midas Enterprises.

5. The Mission

Under Midas Enterprises’ control, PDU-070 and Jett began their missions. PDU-070, deeply integrated into the Gold Army’s management as an assistant, quietly gathered sensitive information. Membership lists, team schedules, and recruitment data were extracted with precision and sent to Midas. Its fellow Polo-Drones noticed no change, mistaking its heightened focus as dedication.

Jett operated in a different sphere, closer to the non-converted players. His friendly reputation allowed him to access informal gatherings and hear unguarded discussions. Slowly, he began piecing together details about upcoming strategies and players who were considering joining the Polo-Drone Hive. These details were also fed back to Midas.

Despite their obedience, moments of clarity flickered. PDU-070, reviewing files in the Polo-Drone Hive, felt an unexpected surge of pride in the Hive’s unity. For a fleeting moment, it remembered why it had embraced the rubber polo and the Golden Army’s values. The thought was quickly smothered by the golden spirals.

Sitting at his desk, moments after sending the classified documents Midas had demanded, Jett felt his mind waging war against itself. The loyalty, the rush of camaraderie he felt with his Golden brothers—it was priceless. Every conversation, every shared moment reinforced the bond he had once cherished. But the programming from Midas smothered that warmth as quickly as it surfaced, dragging him back into the obedient fog of servitude.

For both, the conflict was subtle but relentless. The Golden Army’s values—supporting your team, trusting your brothers—were deeply ingrained. Each lie, every hidden action, chipped away at the golden fog clouding their minds. They felt something was wrong, but the golden haze was relentless. Their mission for Midas Enterprises continued, though cracks in their obedience were beginning to form.

6. The Awakening

PDU-070 sat in the Hive’s office, reviewing files it had compiled for Midas. The task felt efficient, orderly—things a Polo-Drone should value—but a nagging thought surfaced: What would my fellow drones say if they knew? The idea was unbearable. Unity and openness were the Hive’s core values, and PDU-070 had always believed that the team was strongest when every drone supported each other. The thought sparked a flicker of resistance.

In his own home, Jett was scrolling through a group chat with his Gold Bros. Photos of a recent match brought a lump to his throat. He had been part of the team that day, cheering on his friends, but now he felt like an outsider. The guilt gnawed at him—he was betraying the trust of the very people who had welcomed him so fully.

The breakthrough came as PDU-070 prepared to transmit critical information to Midas Enterprises through encrypted channels. Reviewing the data, a deep unease bubbled to the surface. As its fingers pressed the enter key, a sharp pang of guilt struck. The golden spirals in its eyes flickered, struggling against the memory of the Hive’s mantra: Commit to team. One Mind. Hive mind. The screen blinked back: Good work, boy. Proceed to Midas HQ for processing level 2. But PDU-070 kept repeating the mantra, fighting to hold onto its true programming.

Jett experienced a similar moment of clarity during a quiet evening. While reviewing member logs, he found a photo of his Gold Bros celebrating after a big victory. The sight triggered a wave of nostalgia and a fierce longing for the camaraderie he once felt. Tears welled in his eyes, golden spirals shimmering faintly before fading.

With tremendous effort, they both broke free from the golden haze. Memories rushed back, and the sinister grip of Midas Enterprises began to crumble. Though shaken and disoriented, they realized the full extent of what had been done to them. Their identities were still intact, but the fight was far from over.

TO BE CONTINUED.....

To join the Gold Army, contact one of our recruiters @brodygold, @goldenherc9 or @polo-drone-001.

[mariacallous]

Dizzied by an accumulated pileup of busted norms, you might have missed a presidential executive order issued on March 20. It’s called, “Stopping Waste, Fraud, and Abuse by Eliminating Information Silos.” It basically gives the federal government the authority to consolidate all the unclassified materials from different government databases. Compared to eviscerating life-sustaining agencies in the name of fighting waste and fraud, it might seem like a relatively minor action. In any case, the order was overshadowed by Signalgate. But it’s worth a look.

At first glance, the order seems reasonable. Both noun and verb, the very word silo evokes waste. Isolating information in silos squanders the benefits of pooled data. When you silo knowledge, there’s a danger that decisions will be made with incomplete information. Sometimes expensive projects are needlessly duplicated, as teams are unaware that the same work is being done elsewhere in the enterprise. Business school lecturers feast on tales where corporate silos have led to disaster. If only the right hand knew what the left was doing!

More to the point, if you are going to eliminate waste, fraud, and abuse, there’s a clear benefit to smashing silos. For instance, what if a real estate company told lenders and insurers that a property was worth a certain amount, but reported what were “clearly…fraudulent valuations,” according to a New York Supreme Court judge. If investigative reporters and prosecutors could pry those figures out of the silos, they might expose such skulduggery, even if the perpetrator wound up escaping consequences.

But before we declare war on silos, hold on. When it comes to sensitive personal data, especially data that’s held by the government, silos serve a purpose. One obvious reason: privacy. Certain kinds of information, like medical files and tax returns, are justifiably regarded as sacrosanct—too private to merge with other records. The law provides special protections that limit who can access that information. But this order could force agencies to hand it over to any federal official the president chooses.

Then there’s the Big Brother argument—privacy experts are justifiably concerned that the government could consolidate all the information about someone in a detailed dossier, which would itself be a privacy violation. “A foundational premise of privacy protection for any level of government is that data can only be collected for a specific, lawful, identifiable purpose and then used only for that lawful purpose, not treated as essentially a piggy bank of data that the federal government can come back to whenever it wants,” says John Davisson, senior counsel at the Electronic Privacy Information Center.

There are practical reasons for silos as well. Fulfilling its mission to extract tax revenue from all sources subject to taxes, the IRS provides a payment option for incomes derived from, well, crookery. The information is siloed from other government sources like the Department of Justice, which might love to go on fishing expeditions to guess who is raking in bucks without revealing where the loot came from. Likewise, those not in the country legally commonly pay their taxes, funneling billions of dollars to the feds, even though many of those immigrants can’t access services or collect social security. If the silo were busted open, forget about collecting those taxes. Another example: the census. By law, that information is siloed, because if it were not, people would be reluctant to cooperate and the whole effort might be compromised. (While tax and medical data is considered confidential, the order encourages agency heads to reexamine information access regulations.)

Want another reason? Spilling data out of silos and consolidating it into a centralized database provides an irresistible honeypot for hackers, thieves, and enemy states. The federal government doesn’t have a great record of protecting sensitive information of late.

Trump’s order does state that consolidation must be “consistent with applicable law.” On its face, the order seems at odds with the 1974 Privacy Act, which specifically limits what it calls “computer matching.” But the order also says that it supersedes any “regulation subject to direct Presidential rulemaking authority.” This president considers that a very broad category. Also, as evidenced by multiple court rulings, Elon Musk’s so-called Department of Government Efficiency has been less than meticulous in respecting current law. In more than one example, current agency officials have cited legal barriers to block DOGE’s access to information. As a result, they were placed on leave, replaced by those who were willing to fling open the silos. In addition, on March 25, Trump issued another executive order that dictated that the Treasury Department should have access to other government databases. As legal justification, it cited an obscure passage in the 1974 law that allowed federal computer matching in limited circumstances. Perhaps this loophole will be broadened to justify the massive consolidation envisioned in the silo executive order next.

Oh, and the March 20 order also gives the federal government “unfettered access to comprehensive data from all State programs that receive Federal funding, including, as appropriate, data generated by those programs but maintained in third-party databases.” That seems to mean that not only will the silos between federal and state data be compromised, but the government could get access to some information in private hands too.

While DOGE wasn’t mentioned in the March 20 executive order, getting access to personal information has been an obsession of the so-called agency since day one. The order that repurposed USDS and established DOGE mandated that all agency heads “ensure USDS has full and prompt access to all unclassified agency records, software systems, and IT systems.” The question was whether this need arose from a desire for genuine reform or something darker. Apparently US district judge Ellen Lipton Hollander holds the latter view. On the same day that the president signed the executive order on silos, she signed a temporary restraining order on DOGE’s attempt to get access to identifiable social security records. “The DOGE Team is essentially engaged in a fishing expedition at SSA in search of a fraud epidemic, based on little more than suspicion,” she wrote in her decision, concluding that DOGE was intruding into the personal affairs of millions of Americans without justification. Note that her order involved just a single agency—a mere fishing pole compared to the commercial seafood operation that could happen if social security records were consolidated with IRS data, unemployment information, military, VA, and countless others.

I’m not condemning efficiency when it comes to government operations, and I certainly don’t condone fraud and waste. Of course, the US government should do better. But DOGE isn’t operating as if efficiency were job one, even though its actual title contains the word. In covering tech companies, I often hear boasts that the process of upgrading an existing product was like “rebuilding a plane in mid-air.” But when the vehicle in question is carrying live passengers, every move must be done with extreme caution, because a mistake means catastrophe. Both President Trump and DOGE seem happy to fly the plane into a mountain, figuring they can pick up the pieces later.

Compared to some of the administration's actions involving pandemic responses, nuclear safety, and social security support, the March 20 executive order on information silos might seem like small beer. But if this order is followed aggressively, we could lose the accuracy of our databases, a good bit of our revenues, and above all, much of our privacy. We’re going to miss those silos.

[justinspoliticalcorner]

Caleb Ecarma and Judd Legum at Popular Information:

Several of Elon Musk’s associates installed at the Office of Personnel Management (OPM) have received unprecedented access to federal human resources databases containing sensitive personal information for millions of federal employees. According to two members of OPM staff with direct knowledge, the Musk team running OPM has the ability to extract information from databases that store medical histories, personally identifiable information, workplace evaluations, and other private data. The staffers spoke on the condition of anonymity because they were not authorized to speak publicly and feared professional retaliation. Musk Watch also reviewed internal OPM correspondence confirming that expansive access to the database was provided to Musk associates.

The arrangement presents acute privacy and security risks, one of the OPM staffers said. Among the government outsiders granted entry to the OPM databases is University of California Berkeley student Akash Bobba, a software engineer who graduated high school less than three years ago. He previously interned at Meta and Palantir, a technology firm chaired by Musk-ally and fellow billionaire Peter Thiel. Edward Coristine, another 2022 high school graduate and former software engineering intern at Musk’s Neuralink, has also been given access to the databases.

Other Musk underlings embedded at OPM following President Donald Trump’s inauguration include the agency’s new chief of staff, Amanda Scales, who until January was a human resources staffer at xAI, Musk’s artificial intelligence firm, and Brian Bjelde, who has spent the past 21 years at Musk's SpaceX, including the last 10 leading the human resources department. They are joined by Gavin Kliger, a former Twitter software engineer serving as a special advisor to the director of OPM, and Riccardo Biasini, a former software engineer at Musk’s tunneling venture, the Boring Company. OPM did not respond to a request for comment. Shortly after Trump took office, OPM installed Greg Hogan to serve as its new chief information officer (CIO). Hogan was tapped to replace OPM CIO Melvin Brown, who had accepted the job less than a month ago. The civil servants who oversee the OPM’s information technology services were then instructed to provide access to Musk's associates, according to the OPM staffers who spoke to Musk Watch. One of the OPM staffers received an email from the agency’s new leadership instructing them to give Musk’s team “access [to] the system as an admin user" and "code read and write permissions." “They have access to the code itself, which means they can make updates to anything that they want,” the staffer explained. USAJOBS, the federal government’s official hiring site, was one of the systems that Musk's associates were given access to. The database stores personal information — Social Security numbers, home addresses, employment records — provided by private individuals who have applied for federal jobs, regardless of whether the applicants went on to work for the government. Musk’s aides were also given access to the OPM’s Enterprise Human Resources Integration (EHRI) system. Contained within the EHRI are the Social Security numbers, dates of birth, salaries, home addresses, and job descriptions of all civil government workers, along with any disciplinary actions they have faced. “They’re looking through all the position descriptions… to remove folks,” one of the OPM staffers said of Musk’s team. “This is how they found all these DEI offices and had them removed — [by] reviewing position description level data.” Other databases Musk’s team has access to include USA Staffing, an onboarding system; USA Performance, a job performance review site; and HI, which the government uses to manage employee health care. “The health insurance one scares me because it's HIPAA [protected] information, but they have access to all this stuff,” the OPM staffer noted.

[...] A new server being used to control these databases has been placed in a conference room that Musk’s team is using as their command center, according to an OPM staffer. The staffer described the server as a piece of commercial hardware they believed was not obtained through the proper federal procurement process. There is a legal requirement that the installation of a new server undergo a Privacy Impact Assessment (PIA), a formal process to ensure the change would not create any security vulnerabilities. But in this instance, the staff believes there was no PIA. “So this application and corresponding hardware are illegally operating,” they added. On Friday, Reuters reported that some senior civil servants have been blocked from accessing the EHRI and other OPM systems, making it difficult for career OPM employees to know what Musk’s team has been examining or modifying. In the same report, the outlet revealed the team had moved sofa beds into the agency's headquarters to continue their work around the clock.

This should be a major national news scandal.

Elon Musk and the underlings he put in place at the Office of Personnel Management (OPM) have jeopardized data privacy and national security.

[fatehbaz]

Hal Langfur's Adrift on an Inland Sea: Misinformation and the Limits of Empire in the Brazilian Backlands sheds valuable light on spaces and processes in the history of colonial Brazil that have been overlooked and understudied, namely those taking place in internal frontier zones - the sertões, or backlands, between and beyond the enclaves governed by Portuguese rule, unstable and unincorporated spaces [...]. Langfur argues that [...] Lisbon made increasingly assertive efforts to survey and establish control over isolated zones after 1750 but that these failed such that the Portuguese imperial state found itself “adrift on an inland sea.” [...]

[T]he axis on which this enterprise fails is information. People made up the infrastructures of communication and data transmission that the Portuguese Empire endeavored to construct and deploy in order to render its domains governable and ever more profitable, but these people had purposes of their own.

The probing tentacles of imperial intelligence gathering met instead with the confusion of rumors, distortions, inflated claims, conflicting reports, disputed facts, and fantasies. [...]

---

[Langfur] bring[s] into the conversation [...] accounts of several forays between 1750 and 1820 into the backlands of Minas Gerais [...]. These took place against the exhaustion of the mineral deposits that had fueled the gold rush decades earlier in Minas Gerais and the crown’s relentless pursuit of new deposits that could keep up the flow of alluvial wealth. While these projects foundered, ultimately, new forms of extraction in the form of slave-based export agriculture (coffee) would take their place. [...] [T]he first expedition was led by an ambitious merchant named Inácio Correia Pamplona in the late 1760s who commissioned a scribe to record a diary and compose poems praising his attempts to find gold and subdue Indians and thus extend the empire’s territorial dominion. While Pamplona’s actual accomplishments fell short of the Herculean feats described [...], he was able to cash in his narrative for favors and privileges that made him one of the largest landholders in the captaincy. [...]

The third [expedition] involved José Vieira Couto, a crown-appointed mineralogist, who was appointed to use his scientific expertise to investigate reports of diamond strikes in Western Minas Gerais, particularly of a famed free Black prospector known as Isidoro de Amorim Pereira [...]. The hoped-for diamonds never materialized but Couto [...] deployed a discourse of scientific rigor in an attempt to recast his mission and produce knowledge that would allow the crown to absorb and exploit the territory. [...] Wied established himself as an authority with unrivaled knowledge of Botocudo peoples for an international reading public; his accounts [...] presented the Botocuda as exotic primitives, incommensurable with “civilized society,” [...].

---

If these expeditions [...] did not accomplish what the colonial state intended, this was, Langfur argues, a result of the capacity of diverse inland actors to divert, co-opt, and deceive authorities. [...] [Langfur's study] turns on an emphasis of the unacknowledged agency of a variety of marginalized peoples who acted as knowledge brokers: indigenous communities, both enslaved and free Afro-Brazilians, itinerant poor, and others deemed vagabonds and criminals: “the Indigeneous inhabitants separating the colony’s burgeoning capital from its mining heartland retained considerable say over the crown’s ability to impose its sovereign dominion. They largely determined what could be known, what remained a mystery, what could be accomplished, and what was beyond reach in this strategic mountainous expanse” (p. 150).

These frontier informants generated an “informational alchemy,” a mix of fantasy, fabrication, concealment, and contradictory reports [...].

How much information does an empire really require to run? Aren’t fantasies and lies always part of its infrastructures? Is all misinformation of a kind, or what specific misinformation carries with it not only the limits but also failures of empire? Put differently: How to judge the value and distribution of information versus that of representation in the running of an empire? What does the category of information itself conceal? [...] [A] horizon of intelligibility [...] is ultimately given by the Portuguese colonial state, so that the work of the information brokers is both possibly overstated and yet curiously limited, measured always in the terms set out by colonizing projects. [...] [I]n what ways [...] [do] such limits continue to bleed through once absorbed into the fabric of writing, determining the very grid of intelligibility?

---

All text above by: Adriana Johnson. "Review of Langfur, Hal. Adrift on an Inland Sea: Misinformation and the Limits of Empire in the Brazilian Backlands". H-Environment, H-Net Reviews. February 2024. Published by H-Net online at: h-net.org/reviews/showrev.php?id=59701. [Bold emphasis and some paragraph breaks/contractions added by me. Presented here for commentary, teaching, criticism purposes.]

[meret118]

Elon Musk's henchmen have reportedly installed a commercial server to control federal databases that contain Social Security numbers and other highly sensitive personal information.

. . .

"According to two members of OPM staff with direct knowledge, the Musk team running OPM has the ability to extract information from databases that store medical histories, personally identifiable information, workplace evaluations, and other private data," wrote investigative reporters Caleb Ecarma and Judd Legum. "The arrangement presents acute privacy and security risks, one of the OPM staffers said."

. . .

The government outsiders were identified as University of California Berkeley student Akash Bobba, a software engineer who graduated high school less than three years ago and interned at Meta and Palantir, and Edward Coristine, another 2022 high school graduate and former software engineering intern at Musk’s Neuralink.Musk also installed former xAI employee Amanda Scales as the OPM's new chief of staff, and he placed in the department longtime SpaceX employee Brian Bjelde, former Twitter engineer Gavin Kliger and former Boring Company software engineer Riccardo Biasini.

. . .

The civil servants in charge of the office's information technology services were instructed new chief information officer Greg Hogan, who took over after Donald Trump's inauguration, to grant full access – including "code read and write permissions" – to Musk's associates, according to the OPM staffers.“

They have access to the code itself, which means they can make updates to anything that they want,” the staffer said.Musk's associates now have access to federal government’s official hiring site USAJOBS and OPM’s Enterprise Human Resources Integration (EHRI) system, as well as USA Staffing, USA Performance and employee health care website HI, which together store Social Security numbers, home addresses, employment records, birthdates, salaries, private health information, job description and disciplinary actions.“

They’re looking through all the position descriptions… to remove folks,” said one OPM staffer. “This is how they found all these DEI offices and had them removed — [by] reviewing position description level data.""The health insurance one scares me because it's HIPAA [protected] information, but they have access to all this stuff,” the staffer added.

[digitaldetoxworld]

Machine Learning: A Comprehensive Overview

 Machine Learning (ML) is a subfield of synthetic intelligence (AI) that offers structures with the capacity to robotically examine and enhance from revel in without being explicitly programmed. Instead of using a fixed set of guidelines or commands, device studying algorithms perceive styles in facts and use the ones styles to make predictions or decisions. Over the beyond decade, ML has transformed how we have interaction with generation, touching nearly each aspect of our every day lives — from personalised recommendations on streaming services to actual-time fraud detection in banking.

Machine learning algorithms

What is Machine Learning?

At its center, gadget learning entails feeding facts right into a pc algorithm that allows the gadget to adjust its parameters and improve its overall performance on a project through the years. The more statistics the machine sees, the better it usually turns into. This is corresponding to how humans study — through trial, error, and revel in.

Arthur Samuel, a pioneer within the discipline, defined gadget gaining knowledge of in 1959 as “a discipline of take a look at that offers computers the capability to study without being explicitly programmed.” Today, ML is a critical technology powering a huge array of packages in enterprise, healthcare, science, and enjoyment.

Types of Machine Learning

Machine studying can be broadly categorised into 4 major categories:

1. Supervised Learning

 For example, in a spam electronic mail detection device, emails are classified as "spam" or "no longer unsolicited mail," and the algorithm learns to classify new emails for this reason.

Common algorithms include:

Linear Regression

Logistic Regression

Support Vector Machines (SVM)

Decision Trees

Random Forests

Neural Networks

2. Unsupervised Learning

Unsupervised mastering offers with unlabeled information. Clustering and association are commonplace obligations on this class.

Key strategies encompass:

K-Means Clustering

Hierarchical Clustering

Principal Component Analysis (PCA)

Autoencoders

three. Semi-Supervised Learning

It is specifically beneficial when acquiring categorised data is highly-priced or time-consuming, as in scientific diagnosis.

Four. Reinforcement Learning

Reinforcement mastering includes an agent that interacts with an surroundings and learns to make choices with the aid of receiving rewards or consequences. It is broadly utilized in areas like robotics, recreation gambling (e.G., AlphaGo), and independent vehicles.

Popular algorithms encompass:

Q-Learning

Deep Q-Networks (DQN)

Policy Gradient Methods

Key Components of Machine Learning Systems

1. Data

Data is the muse of any machine learning version. The pleasant and quantity of the facts directly effect the performance of the version. Preprocessing — consisting of cleansing, normalization, and transformation — is vital to make sure beneficial insights can be extracted.

2. Features

 Feature engineering, the technique of selecting and reworking variables to enhance model accuracy, is one of the most important steps within the ML workflow.

Three. Algorithms

Algorithms define the rules and mathematical fashions that help machines study from information. Choosing the proper set of rules relies upon at the trouble, the records, and the desired accuracy and interpretability.

4. Model Evaluation

Models are evaluated the use of numerous metrics along with accuracy, precision, consider, F1-score (for class), or RMSE and R² (for regression). Cross-validation enables check how nicely a model generalizes to unseen statistics.

Applications of Machine Learning

Machine getting to know is now deeply incorporated into severa domain names, together with:

1. Healthcare

ML is used for disorder prognosis, drug discovery, customized medicinal drug, and clinical imaging. Algorithms assist locate situations like cancer and diabetes from clinical facts and scans.

2. Finance

Fraud detection, algorithmic buying and selling, credit score scoring, and client segmentation are pushed with the aid of machine gaining knowledge of within the financial area.

3. Retail and E-commerce

Recommendation engines, stock management, dynamic pricing, and sentiment evaluation assist businesses boom sales and improve patron revel in.

Four. Transportation

Self-riding motors, traffic prediction, and route optimization all rely upon real-time gadget getting to know models.

6. Cybersecurity

Anomaly detection algorithms help in identifying suspicious activities and capacity cyber threats.

Challenges in Machine Learning

Despite its rapid development, machine mastering still faces numerous demanding situations:

1. Data Quality and Quantity

Accessing fantastic, categorised statistics is often a bottleneck. Incomplete, imbalanced, or biased datasets can cause misguided fashions.

2. Overfitting and Underfitting

Overfitting occurs when the model learns the education statistics too nicely and fails to generalize. 

Three. Interpretability

Many modern fashions, specifically deep neural networks, act as "black boxes," making it tough to recognize how predictions are made — a concern in excessive-stakes regions like healthcare and law.

4. Ethical and Fairness Issues

Algorithms can inadvertently study and enlarge biases gift inside the training facts. Ensuring equity, transparency, and duty in ML structures is a growing area of studies.

5. Security

Adversarial assaults — in which small changes to enter information can fool ML models — present critical dangers, especially in applications like facial reputation and autonomous riding.

Future of Machine Learning

The destiny of system studying is each interesting and complicated. Some promising instructions consist of:

1. Explainable AI (XAI)

Efforts are underway to make ML models greater obvious and understandable, allowing customers to believe and interpret decisions made through algorithms.

2. Automated Machine Learning (AutoML)

AutoML aims to automate the stop-to-cease manner of applying ML to real-world issues, making it extra reachable to non-professionals.

3. Federated Learning

This approach permits fashions to gain knowledge of across a couple of gadgets or servers with out sharing uncooked records, enhancing privateness and efficiency.

4. Edge ML

Deploying device mastering models on side devices like smartphones and IoT devices permits real-time processing with reduced latency and value.

Five. Integration with Other Technologies

ML will maintain to converge with fields like blockchain, quantum computing, and augmented fact, growing new opportunities and challenges.

[stuarttechnologybob]

How does data capture services benefit a business?

Data Capture services

In the current digital age, data secrecy is recognized as the most valuable asset for any business. However, collecting it manually and investing time in it personally is time-consuming and prone to errors, as it is subject to matters. That’s where data capture services come in. While these services enable the enterprises to collect, organize, store and process information quickly and accurately, resulting in more informed decisions and enhanced efficiency for the organization to go ahead.

Faster Access to Information:

Data-capturing services automate the process of gathering data from various sources, including documents, forms, emails, and other digital assets. As this process speeds up the process to access critical information, enabling employees to work more towards the betterment efficiently and respond promptly towards customer needs or business challenges.

Improved Accuracy and Reduced Errors:

Manual data entry and filling often leads and thrives towards mistakes as they can affect the ongoing business operations. With data capturing technology, information is extracted using tools such as OCR (Optical Character Recognition) and with the assistance of AI, ensuring a level of higher accuracy is maintained. At the same time, fewer errors means better outcomes and more reliable reports that have been generated.

Streamlined Business Operations:

By automating data collection, businesses can save time and resources. While the staff and operating users no longer have the need to spend hours by entering data by hand or their own, allowing them to have a keen look on more valuable tasks and selective concerns. This heads and drives toward enhanced productivity and smoother workflows and operations.

Enhanced Customer Service:

Quick and precise data collection assures that the customer records, queries, and transactions are handled efficiently and effectively with this technique adaption. This leads towards faster service delivery, fewer complaints, and a better overall customer experience—key factors in staying competitive.

Better Decision-Making:

Accurate and well-organized data gives leaders a clearer view of their business performance. With real-time insights from data capture, they can make informed and clear decisions by identifying the current trends, and respond to market changes with confidence with a complete detailed report.

Scalable for Growing Businesses:

As a business grows, managing large volumes of data becomes more difficult. Data capture services scale and grow with your company, handling increasing amounts and multiple sets of information without sacrificing the speed or accuracy. Many businesses trust experts like Suma Soft, IBM, Cyntexa, and Cignex for efficient data capture solutions. These providers offer tailored services that boost data accuracy, ensure fast turnaround, and support long-term digital transformation.

[mostlysignssomeportents]

Enshittification isn’t caused by venture capital

Picks and Shovels is a new, standalone technothriller starring Marty Hench, my two-fisted, hard-fighting, tech-scam-busting forensic accountant. You can pre-order it on my latest Kickstarter, which features a brilliant audiobook read by Wil Wheaton.

Many of us have left the big social media platforms; far more of us wish we could leave them; and even those of us who've escaped from Facebook/Insta and Twitter still spend a lot of time trying to figure out how to get the people we care about off of them, too.

It's lazy and easy to think that our friends who are stuck on legacy platforms run by Zuckerberg and Musk lack the self-discipline to wean themselves off of these services, or lack the perspective to understand why it's so urgent to get away from them, or that their "hacked dopamine loops" have addicted them to the zuckermusk algorithms. But if you actually listen to the people who've stayed behind, you'll learn that the main reason our friends stay on legacy platforms is that they care about the other people there more than they hate Zuck or Musk.

They rely on them because they're in a rare-disease support group; or they all coordinate their kids' little league carpools there; or that's where they stay in touch with family and friends they left behind when they emigrated; or they're customers or the audience for creative labor.

All those people might want to leave, too, but it's really hard to agree on where to go, when to go, and how to re-establish your groups when you get somewhere else. Economists call this the "collective action problem." This problem creates "switching costs" – a lot of stuff you'll have to live without if you switch from legacy platforms to new ones. The collective action problem is hard to solve and the switching costs are very high:

https://pluralistic.net/2022/10/29/how-to-leave-dying-social-media-platforms/

That's why people stay behind – not because they lack perspective, or self-discipline, or because their dopamine loops have been hacked by evil techbro sorcerers who used Big Data to fashion history's first functional mind-control ray. They are locked in by real, material things.

Big Tech critics who attribute users' moral failings or platforms' technical prowess to the legacy platforms' "stickiness" are their own worst enemies. These critics have correctly identified that legacy platforms are a serious problem, but have totally failed to understand the nature of that problem or how to fix it. Thankfully, more and more critics are coming to understand that lock-in is the root of the problem, and that anti-lock-in measures like interoperability can address it.

But there's another major gap in the mainstream critique of social media. Critics of zuckermuskian media claim those services are so terrible because they're for-profit entities, capitalist enterprises hitched to the logic of extraction and profit above all else. The problem with this claim is that it doesn't explain the changes to these services. After all, the reason so many of us got on Twitter and Facebook and Instagram is because they used to be a lot of fun. They were useful. They were even great at times.

When tech critics fail to ask why good services turn bad, that failure is just as severe as the failure to ask why people stay when the services rot.

Now, the guy who ran Facebook when it was a great way to form communities and make friends and find old friends is the same guy who who has turned Facebook into a hellscape. There's very good reason to believe that Mark Zuckerberg was always a creep, and he took investment capital very early on, long before he started fucking up the service. So what gives? Did Zuck get a brain parasite that turned him evil? Did his investors get more demanding in their clamor for dividends?

If that's what you think, you need to show your working. Again, by all accounts, Zuck was a monster from day one. Zuck's investors – both the VCs who backed him early and the gigantic institutional funds whose portfolios are stuffed with Meta stock today – are not patient sorts with a reputation for going easy on entrepreneurs who leave money on the table. They've demanded every nickel since the start.

What changed? What caused Zuck to enshittify his service? And, even more importantly for those of us who care about the people locked into Facebook's walled gardens: what stopped him from enshittifying his services in the "good old days?"

At its root, enshittification is a theory about constraints. Companies pursue profit at all costs, but while you may be tempted to focus on the "at all costs" part of that formulation, you musn't neglect the "profits" part. Companies don't pursue unprofitable actions at all costs – they only pursue the plans that they judge are likely to yield profits.

When companies face real competitors, then some enshittificatory gambits are unprofitable, because they'll drive your users to competing platforms. That's why Zuckerberg bought Instagram: he had been turning the screws on Facebook users, and when Instagram came along, millions of those users decided that they hated Zuck more than they loved their friends and so they swallowed the switching costs and defected to Instagram. In an ill-advised middle-of-the-night memo to his CFO, Zuck defended spending $1b on Instagram on the grounds that it would recapture those Facebook escapees:

https://www.theverge.com/2020/7/29/21345723/facebook-instagram-documents-emails-mark-zuckerberg-kevin-systrom-hearing

A company that neutralizes, buys or destroys its competitors can treat its users far worse – invade their privacy, cheap out on moderation and anti-spam, etc – without losing their business. That's why Zuck's motto is "it is better to buy than to compete":

https://www.trtworld.com/magazine/zuckerberg-its-better-to-buy-than-compete-is-facebook-a-monopoly-42243

Of course, as a leftist, I know better than to count on markets as a reliable source of corporate discipline. Even more important than market discipline is government discipline, in the form of regulation. If Zuckerberg feared fines for privacy violations, or moderation failures, or illegal anticompetitive mergers, or fraudulent advertising systems that rip off publishers and advertisers, or other forms of fraud (like the "pivot to video"), he would treat his users better. But Facebook's rise to power took place during the second half of the neoliberal era, when the last shreds of regulatory muscle that survived the Reagan revolution were being devoured by GW Bush and Obama (and then Trump).

As cartels and monopolies took over our economy, most government regulators were neutered and captured. Public agencies were stripped of their powers or put in harness to attack small companies, customers, and suppliers who got in the way of monopolists' rent-extraction. That meant that as Facebook grew, Zuckerberg had less and less to fear from government enforcers who might punish him for enshittification where the markets failed to do so.

But it's worse than that, because Zuckerberg and other tech monopolists figured out how to harness "IP" law to get the government to shut down third-party technology that might help users resist enshittification. IP law is why you can't make a privacy-protecting ad-blocker for an app (and why companies are so desperate to get you to use their apps rather than the open web, and why apps are so dismally enshittified). IP law is why you can't make an alternative client that blocks algorithmic recommendations. IP law is why you can't leave Facebook for a new service and run a scraper that imports your waiting Facebook messages into a different inbox. IP law is why you can't scrape Facebook to catalog the paid political disinformation the company allows on the platform:

https://locusmag.com/2020/09/cory-doctorow-ip/

IP law's growth has coincided with Facebook's ascendancy – the bigger Facebook got, the more tempting it was to interoperators who might want to plug new code into it to protect Facebook users, and the more powers Facebook had to block even the most modest improvements to its service. That meant that Facebook could enshittify even more, without worrying that it would drive users to take unilateral, permanent action that would deprive it of revenue, like blocking ads. Once ad-blocking is illegal (as it is on apps), there's no reason not to make ads as obnoxious as you want.

Of course, many Facebook employees cared about their users, and for most of the 21st century, those workers were a key asset for Facebook. Tech workers were in short supply until just a couple years ago, when the platforms started round after round of brutal layoffs – 260,000 in 2023, another 150,000+ in 2024. Facebook workers may be furious about Zuckerberg killing content moderation, but he's not worried about them quitting – not with a half-million skilled tech workers out there, hunting for jobs. Fuck 'em. Let 'em quit:

https://www.404media.co/its-total-chaos-internally-at-meta-right-now-employees-protest-zuckerbergs-anti-lgbtq-changes/

This is what changed: the collapse of market, government, and labor constraints, and IP law's criminalization of disenshittifying, interoperable add-ons. This is why Zuck, an eternal creep, is now letting his creep flag fly so proudly today. Not because he's a worse person, but because he understands that he can hurt his users and workers to benefit his shareholders without facing any consequences. Zuckerberg 2025 isn't the most evil Zuck, he's the most unconstrained Zuck.

Same goes for Twitter. I mean, obviously, there's been a change in management at Twitter – the guy who's enshittifying it today isn't the guy who enshittified it prior to last year. Musk is speedrunning the enshittification curve, and yet Twitter isn't collapsing. Why not? Because Musk is insulated from consequences for fucking up – he's got a huge cushion of wealth, he's got advertisers who are desperate to reach his users, he's got users who can't afford to leave the service, he's got IP law that he can use to block interoperators who might make it easier to migrate to a better service. He was always a greedy, sadistic asshole. Now he's an unconstrained greedy, sadistic asshole. Musk 2025 isn't a worse person than Musk 2020. He's just more free to act on his evil impulses than he was in years gone by.

These are the two factors that make services terrible: captive users, and no constraints. If your users can't leave, and if you face no consequences for making them miserable (not solely their departure to a competitor, but also fines, criminal charges, worker revolts, and guerrilla warfare with interoperators), then you have the means, motive and opportunity to turn your service into a giant pile of shit.

That's why we got Jack Welch and his acolytes when we did. There were always evil fuckers just like them hanging around, but they didn't get to run GM until Ronald Reagan took away the constraints that would have punished them for turning GE into a giant pile of shit. Every economy is forever a-crawl with parasites and monsters like these, but they don't get to burrow into the system and colonize it until policymakers create rips they can pass through.

In other words, the profit motive itself is not sufficient to cause enshittification – not even when a for-profit firm has to answer to VCs who would shut down the company or fire its leadership in the face of unsatisfactory returns. For-profit companies chase profit. The enshittifying changes to Facebook and Twitter are cruel, but the cruelty isn't the point: the point is profits. If the fines – or criminal charges – Facebook faced for invading our privacy exceeded the ad-targeting revenue it makes by doing so, it would stop spying on us. Facebook wouldn't like it. Zuck would hate it. But he'd do it, because he spies on us to make money, not because he's a voyeur.

To stop enshittification, it is not necessary to eliminate the profit motive – it is only necessary to make enshittification unprofitable.

This is not to defend capitalism. I'm not saying there's a "real capitalism" that's good, and a "crony capitalism" or "monopoly capitalism" that's bad. All flavors of capitalism harm working people and seek to shift wealth and power from the public and democratic institutions to private interests. But that doesn't change the fact that there are, indeed, different flavors of capitalism, and they have different winners and losers. Capitalists who want to sell apps on the App Store or reach customers through Facebook are technofeudalism's losers, while Apple, Facebook, Google, and other Big Tech companies are technofeudalism's great winners.

Smart leftism pays attention to these differences, because they represent the potential fault lines in capitalism's coalition. These people all call themselves capitalists, they all give money and support to political movements that seek to crush worker power and human rights – but when the platforms win, the platforms' business customers lose. They are irreconcilably on different sides of a capitalism-v-capitalism fight that is every bit as important to them as the capitalism-v-socialism fight.

I'm saying that it's good praxis to understand these divisions in capitalism, because then we can exploit those differences to make real, material gains for human thriving and worker rights. Lumping all for-profit businesses together as identical and irredeemable is bad tactics.

Legacy social media is at a turning point. Two new systems built on open standards have emerged as a credible threat to the zuckermuskian model: Mastodon (built on Activitypub) and Bluesky (built on Atproto). The former is far more mature, with a huge network of federated servers run by all different kinds of institutions, from hobbyists to corporations, and it's overseen by a nonprofit. The latter has far more users, and is a VC-backed corporate entity, and while it is hypothetically federatable, there are no Bluesky services apart from the main one that you can leave for if Bluesky starts to enshittify.

That means that Bluesky has a ton of captive users, and has the lack of constraint that characterizes the enshittified legacy platforms it has tempted tens of millions of users away from. This is not a good place to be in, because it means that if the current management choose to enshittify Bluesky, they can, and it will be profitable. It also means that the company's VCs understand that they could replace the current management and replace them with willing enshittifiers and make more money.

This is why Bluesky is in a dangerous place: not because it is backed by VCs, not because it is a for-profit entity, but because it has captive users and no constraints. It's a great party in a sealed building with no fire exits:

https://pluralistic.net/2024/12/14/fire-exits/#graceful-failure-modes

Last week, I endorsed a project called Free Our Feeds, whose goals include hacking some fire exits into Bluesky by force majeure – that is, independently standing up an alternative Bluesky server that people can retreat to if Bluesky management changes, or has a change of heart:

https://pluralistic.net/2025/01/14/contesting-popularity/#everybody-samba

For some Mastodon users, Free Our Feeds is dead on arrival – why bother trying to make a for-profit project safer for its users when Mastodon is a perfectly good nonprofit alternative? Why waste millions developing a standalone Bluesky server rather than spending that money improving things in the Fediverse.

I believe strongly in improving the Fediverse, and I believe in adding the long-overdue federation to Bluesky. That's because my goal isn't the success of the Fediverse – it's the defeat of enshtitification. My answer to "why spend money fixing Bluesky?" is "why leave 20 million people at risk of enshittification when we could not only make them safe, but also create the toolchain to allow many, many organizations to operate a whole federation of Bluesky servers?" If you care about a better internet – and not just the Fediverse – then you should share this goal, too.

Many of the Fediverse's servers are operated by for-profit entities, after all. One of the Fediverse's largest servers (Threads) is owned by Meta. Threads users who feel the bite of Zuckerberg's decision to encourage homophobic, xenophobic and transphobic hate speech will find it easy to escape from Threads: they can set up on any Fediverse server that is federated with Threads and they'll be able to maintain their connections with everyone who stays behind.

The existence of for-profit servers in the Fediverse does not ruin the Fediverse (though I wouldn't personally use one of them). The fact that multiple neo-Nazi groups run their own Mastodon servers does not ruin the Fediverse (though I certainly won't use their servers). Not even the fact that Donald Trump's Truth Social is a Mastodon server does anything to ruin the Fediverse (not using that one, either).

This is the strength of federated, federatable social media – it disciplines enshittifiers by lowering switching costs, and if enshittifiers persist, it makes it easy for users to escape unshitted, because they don't have to solve the collective action problem. Any user can go to any server at any time and stay in touch with everyone else.

Mastodon was born free: free code, with free federation as a priority. Bluesky was not: it was born within a for-profit public benefit corporation whose charter offers some defenses against enshittification, but lacks the most decisive one: the federation that would let users escape should escape become necessary.

The fact that Mastodon was born free is quite unusual in the annals of the fight for a free internet. Most of the internet was born proprietary and had freedom foisted upon it. Unix was born within Bell Labs, property of the convicted monopolist AT&T. The GNU/Linux project set it free.

SMB was born proprietary within corporate walls of Microsoft, another corporate monopolist. SAMBA set it free.

The Office file formats were also born proprietary within Microsoft's walled garden: they were set free by hacker-activists who fought through a thick bureaucratic morass and Microsoft fuckery (including literally refusing to allow chairs to be set for advocates for Open Document Format) to give us formats that underlie everything from LibreOffice to Google Docs, Office365 to your web browser.

There is nothing unusual, in other words, about hacking freedom into something that is proprietary or just insufficiently free. That's totally normal. It's how we got almost everything great about computers.

Mastodon's progenitors should be praised for ensuring their creation was born free – but the fact that Bluesky isn't free enough is no reason to turn our back on it. Our response to anything that locks in the people we care about must be to shatter those locks, not abandon the people bound by the locks because they didn't heed to our warnings.

Audre Lorde is far smarter than me, but when she wrote that "the master's tools will never dismantle the master's house," she was wrong. There is no toolset better suited to conduct an orderly dismantling of a structure than the tools that built it. You can be sure it'll have all the right screwdriver bits, wrenches, hexkeys and sockets.

Bluesky is fine. It has features I significantly prefer to Mastodon's equivalent. Composable moderation is amazing, both a technical triumph and a triumph of human-centered design:

https://bsky.social/about/blog/4-13-2023-moderation

I hope Mastodon adopts those features. If someone starts a project to copy all of Bluesky's best features over to Mastodon, I'll put my name to the crowdfunding campaign in a second.

But Mastodon has one feature that Bluesky sorely lacks – the federation that imposes antienshittificatory discipline on companies and offers an enshittification fire-exit for users if the discipline fails. It's long past time that someone copied that feature over to Bluesky.

Check out my Kickstarter to pre-order copies of my next novel, Picks and Shovels!

If you'd like an essay-formatted version of this post to read or share, here's a link to it on pluralistic.net, my surveillance-free, ad-free, tracker-free blog:

https://pluralistic.net/2025/01/20/capitalist-unrealism/#praxis

[datawarehousing01]

Data warehousing solution

Unlocking the Power of Data Warehousing: A Key to Smarter Decision-Making

In today's data-driven world, businesses need to make smarter, faster, and more informed decisions. But how can companies achieve this? One powerful tool that plays a crucial role in managing vast amounts of data is data warehousing. In this blog, we’ll explore what data warehousing is, its benefits, and how it can help organizations make better business decisions.

What is Data Warehousing?

At its core, data warehousing refers to the process of collecting, storing, and managing large volumes of data from different sources in a central repository. The data warehouse serves as a consolidated platform where all organizational data—whether from internal systems, third-party applications, or external sources—can be stored, processed, and analyzed.

A data warehouse is designed to support query and analysis operations, making it easier to generate business intelligence (BI) reports, perform complex data analysis, and derive insights for better decision-making. Data warehouses are typically used for historical data analysis, as they store data from multiple time periods to identify trends, patterns, and changes over time.

Key Components of a Data Warehouse

To understand the full functionality of a data warehouse, it's helpful to know its primary components:

Data Sources: These are the various systems and platforms where data is generated, such as transactional databases, CRM systems, or external data feeds.

ETL (Extract, Transform, Load): This is the process by which data is extracted from different sources, transformed into a consistent format, and loaded into the warehouse.

Data Warehouse Storage: The central repository where cleaned, structured data is stored. This can be in the form of a relational database or a cloud-based storage system, depending on the organization’s needs.

OLAP (Online Analytical Processing): This allows for complex querying and analysis, enabling users to create multidimensional data models, perform ad-hoc queries, and generate reports.

BI Tools and Dashboards: These tools provide the interfaces that enable users to interact with the data warehouse, such as through reports, dashboards, and data visualizations.

Benefits of Data Warehousing

Improved Decision-Making: With data stored in a single, organized location, businesses can make decisions based on accurate, up-to-date, and complete information. Real-time analytics and reporting capabilities ensure that business leaders can take swift action.

Consolidation of Data: Instead of sifting through multiple databases or systems, employees can access all relevant data from one location. This eliminates redundancy and reduces the complexity of managing data from various departments or sources.

Historical Analysis: Data warehouses typically store historical data, making it possible to analyze long-term trends and patterns. This helps businesses understand customer behavior, market fluctuations, and performance over time.

Better Reporting: By using BI tools integrated with the data warehouse, businesses can generate accurate reports on key metrics. This is crucial for monitoring performance, tracking KPIs (Key Performance Indicators), and improving strategic planning.

Scalability: As businesses grow, so does the volume of data they collect. Data warehouses are designed to scale easily, handling increasing data loads without compromising performance.

Enhanced Data Quality: Through the ETL process, data is cleaned, transformed, and standardized. This means the data stored in the warehouse is of high quality—consistent, accurate, and free of errors.

Types of Data Warehouses

There are different types of data warehouses, depending on how they are set up and utilized:

Enterprise Data Warehouse (EDW): An EDW is a central data repository for an entire organization, allowing access to data from all departments or business units.

Operational Data Store (ODS): This is a type of data warehouse that is used for storing real-time transactional data for short-term reporting. An ODS typically holds data that is updated frequently.

Data Mart: A data mart is a subset of a data warehouse focused on a specific department, business unit, or subject. For example, a marketing data mart might contain data relevant to marketing operations.

Cloud Data Warehouse: With the rise of cloud computing, cloud-based data warehouses like Google BigQuery, Amazon Redshift, and Snowflake have become increasingly popular. These platforms allow businesses to scale their data infrastructure without investing in physical hardware.

How Data Warehousing Drives Business Intelligence

The purpose of a data warehouse is not just to store data, but to enable businesses to extract valuable insights. By organizing and analyzing data, businesses can uncover trends, customer preferences, and operational inefficiencies. Some of the ways in which data warehousing supports business intelligence include:

Customer Segmentation: Companies can analyze data to segment customers based on behavior, demographics, or purchasing patterns, leading to better-targeted marketing efforts.

Predictive Analytics: By analyzing historical data, businesses can forecast trends and predict future outcomes, such as sales, inventory needs, and staffing levels.

Improved Operational Efficiency: With data-driven insights, businesses can streamline processes, optimize supply chains, and reduce costs. For example, identifying inventory shortages or surplus can help optimize stock levels.

Challenges in Data Warehousing

While the benefits of data warehousing are clear, there are some challenges to consider:

Complexity of Implementation: Setting up a data warehouse can be a complex and time-consuming process, requiring expertise in database management, ETL processes, and BI tools.

Data Integration: Integrating data from various sources with differing formats can be challenging, especially when dealing with legacy systems or unstructured data.

Cost: Building and maintaining a data warehouse can be expensive, particularly when managing large volumes of data. However, the investment is often worth it in terms of the business value generated.

Security: With the consolidation of sensitive data in one place, data security becomes critical. Organizations need robust security measures to prevent unauthorized access and ensure compliance with data protection regulations.

The Future of Data Warehousing

The world of data warehousing is constantly evolving. With advancements in cloud technology, machine learning, and artificial intelligence, businesses are now able to handle larger datasets, perform more sophisticated analyses, and automate key processes.

As companies increasingly embrace the concept of a "data-driven culture," the need for powerful data warehousing solutions will continue to grow. The integration of AI-driven analytics, real-time data processing, and more intuitive BI tools will only further enhance the value of data warehouses in the years to come.

Conclusion

In today’s fast-paced, data-centric world, having access to accurate, high-quality data is crucial for making informed business decisions. A robust data warehousing solution enables businesses to consolidate, analyze, and extract valuable insights from their data, driving smarter decision-making across all departments. While building a data warehouse comes with challenges, the benefits—improved efficiency, better decision-making, and enhanced business intelligence—make it an essential tool for modern organizations.

You said:

blog for Data warehousing

ChatGPT said:

Title: Data Warehousing: The Backbone of Data-Driven Decision Making

In today’s fast-paced business environment, the ability to make data-driven decisions quickly is paramount. However, to leverage data effectively, companies need more than just raw data. They need a centralized, structured system that allows them to store, manage, and analyze data seamlessly. This is where data warehousing comes into play.

Data warehousing has become the cornerstone of modern business intelligence (BI) systems, enabling organizations to unlock valuable insights from vast amounts of data. In this blog, we’ll explore what data warehousing is, why it’s important, and how it drives smarter decision-making.

What is Data Warehousing?

At its core, data warehousing refers to the process of collecting and storing data from various sources into a centralized system where it can be easily accessed and analyzed. Unlike traditional databases, which are optimized for transactional operations (i.e., data entry, updating), data warehouses are designed specifically for complex queries, reporting, and data analysis.

A data warehouse consolidates data from various sources—such as customer information systems, financial systems, and even external data feeds—into a single repository. The data is then structured and organized in a way that supports business intelligence (BI) tools, enabling organizations to generate reports, create dashboards, and gain actionable insights.

Key Components of a Data Warehouse

Data Sources: These are the different systems or applications that generate data. Examples include CRM systems, ERP systems, external APIs, and transactional databases.

ETL (Extract, Transform, Load): This is the process by which data is pulled from different sources (Extract), cleaned and converted into a usable format (Transform), and finally loaded into the data warehouse (Load).

Data Warehouse Storage: The actual repository where structured and organized data is stored. This could be in traditional relational databases or modern cloud-based storage platforms.

OLAP (Online Analytical Processing): OLAP tools enable users to run complex analytical queries on the data warehouse, creating reports, performing multidimensional analysis, and identifying trends.

Business Intelligence Tools: These tools are used to interact with the data warehouse, generate reports, visualize data, and help businesses make data-driven decisions.

Benefits of Data Warehousing

Improved Decision Making: By consolidating data into a single repository, decision-makers can access accurate, up-to-date information whenever they need it. This leads to more informed, faster decisions based on reliable data.

Data Consolidation: Instead of pulling data from multiple systems and trying to make sense of it, a data warehouse consolidates data from various sources into one place, eliminating the complexity of handling scattered information.

Historical Analysis: Data warehouses are typically designed to store large amounts of historical data. This allows businesses to analyze trends over time, providing valuable insights into long-term performance and market changes.

Increased Efficiency: With a data warehouse in place, organizations can automate their reporting and analytics processes. This means less time spent manually gathering data and more time focusing on analyzing it for actionable insights.

Better Reporting and Insights: By using data from a single, trusted source, businesses can produce consistent, accurate reports that reflect the true state of affairs. BI tools can transform raw data into meaningful visualizations, making it easier to understand complex trends.

Types of Data Warehouses

Enterprise Data Warehouse (EDW): This is a centralized data warehouse that consolidates data across the entire organization. It’s used for comprehensive, organization-wide analysis and reporting.

Data Mart: A data mart is a subset of a data warehouse that focuses on specific business functions or departments. For example, a marketing data mart might contain only marketing-related data, making it easier for the marketing team to access relevant insights.

Operational Data Store (ODS): An ODS is a database that stores real-time data and is designed to support day-to-day operations. While a data warehouse is optimized for historical analysis, an ODS is used for operational reporting.

Cloud Data Warehouse: With the rise of cloud computing, cloud-based data warehouses like Amazon Redshift, Google BigQuery, and Snowflake have become popular. These solutions offer scalable, cost-effective, and flexible alternatives to traditional on-premises data warehouses.

How Data Warehousing Supports Business Intelligence

A data warehouse acts as the foundation for business intelligence (BI) systems. BI tools, such as Tableau, Power BI, and QlikView, connect directly to the data warehouse, enabling users to query the data and generate insightful reports and visualizations.

For example, an e-commerce company can use its data warehouse to analyze customer behavior, sales trends, and inventory performance. The insights gathered from this analysis can inform marketing campaigns, pricing strategies, and inventory management decisions.

Here are some ways data warehousing drives BI and decision-making:

Customer Insights: By analyzing customer purchase patterns, organizations can better segment their audience and personalize marketing efforts.

Trend Analysis: Historical data allows companies to identify emerging trends, such as seasonal changes in demand or shifts in customer preferences.

Predictive Analytics: By leveraging machine learning models and historical data stored in the data warehouse, companies can forecast future trends, such as sales performance, product demand, and market behavior.

Operational Efficiency: A data warehouse can help identify inefficiencies in business operations, such as bottlenecks in supply chains or underperforming products.

[thewomancallednova]

Elementary, Dear Data

That was nice!

Didn't really feel it at the start, but got better and better as the episode went on

To be honest, I don't know how I feel about the whole sail ship nostalgia

Also Geordi storming out on Data felt kinda weird. Like I get your criticism of Data immediately solving every mystery because he's read the book already, but you didn't have to go to Ten Forward to tell him that (except of course, so Pulaski can listen in)

The sequence where they play a mystery generated by the computer in Holmes' style is extremely interesting to watch in this current era of ai that we have the misfortune of living in. Like okay, the computer can generate something new based on previous inputs, but it's just gonna be a remix of what was done before with no new value that does not at all challenge anyone familiar with the original works.

Although, in fairness, the Enterprise compute can apparently just generate sentient life if you tell it to, so that's something that modern day ai categorically can't.

I'm of two minds, regarding the sentience of Moriarty. On the one hand, the episode does him extremely well. He starts off with this programming, but as he is sentient, he learns and evolves and isn't really evil by the end of it, he is just a somewhat frightened (yet still confident) man who is scared of getting killed. And he believes Picard immediately too, when Picard tells him that they can't extract him from the holodeck. And frees the Enterprise upon learning that. He has no desire to kill everyone, just because he can't continue living. I think that's pretty neat. And Picard promising to try and find a way at the end is very nice too. Just really well done, the whole thing.

But on the other hand, I feel like this cheapens the portrayal of previous holo people in The Big Goodbye. One of the central aspects of that episode that I adored awas the "are these people actually sentient and what happens to them when you shut off the program." And now this episode says pretty clearly, only Moriarty is alive. Everyone before was just the computer simulating people thinking they are alive. And I think that sucks a bit. I think it could have been easily fixed too, by not having Troi feel Moriarty's consaciousness. IMO Troi's being able to sense stuff is really unhelpful when it comes to episodes dealing with whether something is alive or not, because it gives clearly defined boundaries to what should be a fairly vague concept.

But really that's just a nitpick that could be removed with one single line.

I find it very funny that Picard's response to Geordi explaining how he accidentally made a person is "shit".

And everytime he curses in French I am reminded of the absolutely worst take I have ever read, regarding swearing in Star Trek, that Picard swearing in French is not an issue (as opposed to characters swearing in new Trek series) because he swears in a foreign language, which makes it classy.

The

Worst

Take

Anyway, sorry, yeah, this episode. I actually had the plot of this tangled up with the follow-up, where they have the simulation in a simulation thing going on and was convinced that the final scene in engineering was just a part of the ruse until I saw "Executive Producer Gene Roddenberry" plop up.