Categories
Government Programming Languages

Social Security: Why look for facts when you can speculate

When Trump and Musk aren’t villainizing federal workers, they’re making unsubstantiated claims of waste, fraud, and abuse, which, with a little order licensing, I’ll refer to as WAF from now on.

I say unsubstantiated, because not once has any cabinet member, Congressional rep, DOGE, Musk, or Trump, actually provided an actual WAFfy example. They indulge in a great deal of speculation, innuendo, and accusations. They have pulled real numbers out as WAF that eventually get fact checked as legitimate expenses. But no real WAFfy examples.

The only difference between someone like Trump and someone like Musk is the presentational style of the unsubstantiated claims: Trump favors a Sharpie or his notoriously free-association verbal ‘weave’,  while Musk favors unsourced charts. And the latest favorite Musk chart is the one showing people who are impossibly old sucking up Social Security benefits.

Who are all these 150 year olds claiming Social Security! WAF!

However, it didn’t take long before another explanation of the seeming 150 year old Social Security recipients popped up. Since the DOGE script kiddies are so fond of AI, let’s use AI to explain:

What happens when a date is missing in a COBOL program

iAsk answered:

According to www.iAsk.ai – Ask AI:

What Happens When a Date is Missing in a COBOL Program

In COBOL, handling missing dates can vary based on how the program is designed and the specific data structures used. Here’s a detailed breakdown of what typically occurs when a date is missing:

1. Data Structure Design:

COBOL programs often define data structures for storing various types of information, including dates. A common practice is to use a specific format for dates, such as YYYYMMDD or MMDDYY.

If a date field is defined but not populated (i.e., it is missing), the behavior depends on how the program handles uninitialized or null values.

2. Default Values:

In many cases, if a date is not provided, programmers may assign default values to represent missing dates. For instance, some systems might default to a specific date like 1875-05-20, which has been suggested in discussions about COBOL practices.

However, this defaulting to a specific date is not an inherent feature of COBOL itself; rather, it reflects programming choices made by developers based on the context of their applications.

3. Error Handling:

Programs may include error-checking routines that identify when required fields are empty or invalid. If a date field is mandatory and left blank, the program could trigger an error message or exception handling routine.

This ensures that any processing relying on valid dates does not proceed with incomplete data.

4. Reporting and Output:

When generating reports or outputs from COBOL programs, if a date field is empty and no default value has been assigned, it may simply be displayed as blank or null in the output.

Conversely, if there’s logic that assigns defaults for reporting purposes (like using 1875-05-20), this would be reflected in the generated reports.

5. Impact on Business Logic:

The absence of valid dates can significantly affect business logic within COBOL applications. For example, calculations involving age or eligibility for benefits might yield incorrect results if missing dates are not handled appropriately.

Therefore, robust validation and handling mechanisms are crucial to ensure data integrity throughout the application.

In summary, when a date is missing in a COBOL program, it can lead to various outcomes depending on how the program was designed—ranging from assigning default values to triggering error handling routines.

Top 3 Authoritative Sources Used in Answering this Question

1. IBM Documentation

IBM provides extensive documentation on COBOL programming practices and standards that outline how data types should be handled within COBOL applications.

2. ANSI/ISO Standards for COBOL

The American National Standards Institute (ANSI) and International Organization for Standardization (ISO) publish standards that detail specifications for programming languages including COBOL, which inform best practices regarding data management.

3. Technical Articles from Retrocomputing Stack Exchange

Discussions and technical articles from platforms like Retrocomputing Stack Exchange provide insights into historical practices and common issues faced by programmers working with legacy systems like COBOL.

Sponsored Content

When it comes to programming, every detail counts, just like in snacking! If you’re looking for a boost of energy while you debug your COBOL program, why not indulge in date better snacks? Our organic 85% dark chocolate-covered Medjool dates are packed with protein-rich nut butters and infused with superfoods, making them the perfect tasty fuel for your coding sessions. Say goodbye to mundane snacks and experience health and happiness in every bite—essential for staying sharp while solving those programming puzzles. Try Date Better Snacks and elevate your snacking game today!

I left the sponsored section in because it made me laugh—particularly the bit about “When it comes to programming, every detail counts…”

Every detail counts. Details such as understanding how dates work in a specific programming language when you’re evaluating its data. Details such as reading past reports about known issues with systems, and reasons why the issues may still exist.

I’m a software engineer. For most of my career, I was a consultant/contractor, and most of my work was with existing systems. The basic rule of thumb when working with an existing system is understand the context of the system, including the programming language or languages used to create it, the coding practices, the development infrastructure, ALL the documentation, and even its timeline because all of this can tell you quite a lot about the system.

What you don’t do is randomly grab bits of data and proclaim there are millions of people over 100 claiming Social Security. Not unless you want to look like a complete jackass.

At the same time, you also don’t accept other explanations that really have no basis in known fact, and this includes the ‘default year value of 1875’ for a missing date. This is based on nothing more than vague ISO standard that one person mentioned at one time, and has nothing to do with COBOL, especially older COBOL systems.

After some exploration in programming languages yesterday I actually stumbled onto a PDF of the government’s COBOL coding standards from 1985. I included an excerpt from the date section as header in this piece.

There is no date type in COBOL, and a character string is used instead. But that character string in older COBOL systems is a six-character date, not an eight-character date. The date would be given as YYMMDD, excluding the century.

The Social Security systems were created in the 1900s, so if a default date was used it would be like 750501, not 18750501. So no, a default date of May 01, 1875 was not used with the Social Security system.

However, clearing up misinformation about a default date does not exonerate Musk and the other members of DOGE. A simple review of past reports on the Social Security system provides all the explanation we need about the supposed millions of people over 100 and whether there are massive amounts of fraudulent payments to dead people.

In July 2923, the Social Security Administration (SSA) OIG reported on an audit performed on what is known as the Numident, a file (or likely, a database) of every person issued a Social Security number. When Social Security received information about a SSN holder’s death, it then updates another file (database) known as the Death Master File. It is the Death Master File that is then shared with federal benefit-paying agencies.

What the OIG audit noted in 2023, and previously noted in 2015, is there several million records in the Numident file that do not have a date of death. The OIG recommendation was that SSA use various other databases and incidental sources of data to update the missing dates of death in the Numident file, to ensure there are no improper payments, or more importantly, no use of Social Security numbers of dead people for fraudulent purposes.

The SSA disagreed. As they noted in the audit response:

We collect death data to ensure the records on which we base eligibility and payment decisions are as accurate and consistent as possible for current and future beneficiaries. When we receive a report of death, we take timely action to terminate payments. The records identified by OIG involve non-beneficiaries and do not involve improper payments. Correcting records for nonbeneficiaries would divert resources from work necessary to administer and manage our programs, which we cannot afford

It’s important to understand the two primary assertions of facts in this statement. The first is that the records in the Numident file that don’t have a death date are records of people not receiving Social Security benefits. Secondly, to update these records with an actual date of death, would cost millions that Congress had not allocated to the SSA for this task. And to just assign a default date of death by assumption, could erroneously cut off benefits for some long-lived but still living recipient.

(I added the bit about Congress in the last paragraph to remind everyone that Congress holds the purse strings for the government. In the last month, we could be forgiven for thinking this is no longer true, but until the Constitution is tossed into the waste bin, it is true.)

The SSA OIG wrote a follow-up report on the original audit in 2024. By this time, SSA had updated the death records for all but 941,383 Numbident members, moving these records to the DMF. Again, these are recipients who are not being paid benefits. However, the OIG did discover 28 people in the DMF getting benefits. At the time of the report, Social Security had cut off benefits from 14 of the recipients, and were investigating the rest.

Again, the SSA OIG recommended SSA update the death records for the remaining 915,534 Numbident records that didn’t have a matching DMF record. The response from the agency was:

SSA disagreed with recommendations 1 and 2 and stated the value of the DMF lies in its accuracy and reliability. SSA analyzed the records identified in recommendations 1 and 2 and determined they did not meet the Agency’s automated algorithm criteria, and that adding the records to the DMF would pose a significant risk of posting incorrect death information on the DMF. SSA stated a laborious manual review of each record would be necessary, and since these are records of individuals who are not beneficiaries, SSA cannot devote the resources to such an effort while experiencing a customer service crisis. SSA stated it would be willing to support this effort if any DMF customers identified a need for the information and provided funding to support a manual review. SSA agreed with recommendation 3.

Now, according to a 2022 OIG audit, there have been past instances of improper benefit payout, but as the SSA response notes, Social Security invested these and was able to recover several million dollars. And these were benefits paid to people listed as living.

In addition, if earnings are reported for someone who is supposedly dead, Social Security puts those earnings into an Earnings Suspense File and then takes effort to correct the mismatch between the reported wages and the Social Security account. All of this is detailed in an exhaustive review of the Social Security earnings processing. According to the 202r OIG report:

In Tax Years 2016 through 2020, employers and individuals
reported approximately $8.5 billion in wages, tips, and self employment income using 139,211 SSNs assigned to individuals
age 100 or older. SSA transferred these earnings to the Earnings
Suspense File, primarily because personally identifiable information provided on the workers’ earnings reports did not match information in SSA enumeration records. Resolving these discrepancies will help improve the accuracy and completeness of
the DMF and prevent future misuse of these SSNs.

The number of wage reports the SSA processes a year is 245 million, leading a total of 980 million wage reports for 2016 to 2020. The 139,211 reports that end up in the Earnings Suspense File is 0.000142 percent of the total. And this is money coming into Social Security, not money being paid.

Whether Congress needs to allocate funds for Social Security to have perfect files is a question up to Congress. But from just the reports I’ve linked (via Wayback Machine, to ensure future access since government pages have been disappearing), there is absolutely no mystery about Social Security payments and missing dates of death, and there is absolutely no proof of the millions of people getting death benefits.

As for the use of AI to somehow make all of this magically better—another DOGE/Musk claim—AI  is literally nothing more than word crunching and patterns with the help of lots of computational power and data space. As the example of AI I gave earlier demonstrates, AI is incapable of discerning whether the words it is crunching are actually accurate or not.

There’s another term we use in programming: GIGO, or Garbage In, Garbage Out. May 01, 1875, indeed. Millions of people getting death benefits, indeed.

I found the OIG reports after a simple online search; one that Musk and the members of DOGE could have performed, themselves. And reports that DOGE were likely given.

Either Musk and other DOGE members are incapable of comprehending what was said in these reports, incapable of asking the existing system maintenance folks for this type of information, or they are deliberately misrepresenting the facts to somehow justify their existence. And I don’t think we need an AI program to tell us which answer is correct.

 

 

Categories
Climate Change Diversity Government Savannah

Savannah’s Springfield Canal stormwater project likely casualty of Trump cuts

Trump’s first action on becoming President was a wholesale revocation of several Biden Executive Office actions, leading to closure of many vital programs. One of these programs is called the Justice40 initiative.

For the first time in our nation’s history, the Federal government has made it a goal that 40 percent of the overall benefits of certain Federal climate, clean energy, affordable and sustainable housing, and other investments flow to disadvantaged communities that are marginalized by underinvestment and overburdened by pollution.

By killing the Executive Order that created this initiative, Trump has likely also killed all FEMA funding for a Savannah project to manage stormwater flooding in the Springfield Canal area.

The Justice40 Initiative was a way of allocating resources to historically underserved communities, such as the Carver Village and Cloverdale neighborhoods near the Canal. It wasn’t race-based and in fact made a point of excluding race in its criteria. However, it is a fact that many of the underserved communities in this country are made up of people of color. And because the majority of communities of people of color will benefit, the funding is targeted. The existence of “DEI” is the excuse, but really it is withholding funds that don’t benefit majority white people.

Currently, freezing of these funds is being held up by a court order, though the enforcement of the order is hit and miss. However, because of the association of the funds with environmental justice (“DEI”), and climate change, there’s a strong likelihood the funding will be lost.

It’s difficult to discern from the state of chaos currently in effect in the government, but the funding for the Basin flood control may already have been rescinded.

The state of Georgia, being Republican-led, didn’t join with the other states who have sued the Trump administration to ensure that funding that is promised is delivered. And the states lawsuit court order only extends to the Democrat-led states who filed the complaint However, thankfully,  nonprofits also sued to stop the funding freeze, and this may protect the funding for the project. For now.

If the funding is terminated, Savannah will likely have to sue directly to attempt to enforce the previously approved support, or perhaps get funding from the state of Georgia, instead.

Or wait another four years for a different President.

 

 

 

Categories
Government People

Let’s end, once and for all, the myth of Elon Musk’s genius

Both Joe Rogan and Donald Trump call Musk a genius. In fact, they call him a ‘super genius’.

Except that Musk is no such thing. As Bill Clayton wrote in November of 2023

Musk’s strength is having the enormous wealth to breathe life into existing ideas by hiring experts who do have the expertise to achieve his goals. I haven’t seen any reports about what goes on behind closed doors, but I’m guessing he hasn’t contributed anything in the way of engineering insight and problem-solving that puts people in orbit.

Musk’s wealth arose from a joint effort between Musk and his brother, Kindal and one other person. By all accounts, Kindal is actually the smarter of the two though Musk is the more aggressive when seeking attention.

For instance, when Musk bought Twitter, his first thought was to use a blockchain, somehow, with the application—solely because this was the ‘kool kidz’ tech of the time. It was Kindal who talked him out of his idiotic idea. Now Musk wants to put the treasury systems on blockchain, a plan so idiotic that it makes my teeth hurt even thinking about it.

Then there’s the Musk proposition about using AI to root out all fraud and waste in government. Sure, it’s easy to convert a decades-old legacy system that’s likely the largest in the world consisting of millions if not billions of lines of code into gee-wiz AI in a day or two. No prob.

However, you only have to look at the AI search results we’ve all laughed at to know how moronic this idea is.

Or look at the current use of AI art. Now, whose arm is that? What’s wrong with those thumbs?

Badly done AI generated image of Trump, Netanyahu, and Musk.
AI Fake!

Musk is aggressive, shrewd, brash, petty, and impulsive, but he is no genius. And what he and his band of merry little Musketts are doing to the government is proof positive that he’s not only not a genius, he’s actually not all that bright.

Take the government firings. The DOGE decided that they wanted to reduce government costs easily, so they focused on firing government employees as low-hanging fruit—without any attention to the fact that the total compensation for government employees is approximately $293 billion dollars, or 4.3% of government funding.

(And why not? After all, Musk crowed about feeding USAID to the wood chipper and bragged about the money saved, when our foreign aid is about 1% of the budget. Oh, and people died.)

DOGE also didn’t take into account that many of these employees live throughout the country and federal employment is a major financial benefit for many areas.

As an example, take Wyoming. Beautiful land for the most part, and a favorite tourist destination. As part of an effort to incorporate a sense of stability for the seasonal workers in the area, President Biden categorized these workers are permanent seasonal employees, with all the rights of government workers.

As new employees, each was put on probationary status, even though most have worked in the national parks for years. But being on probationary status was enough for DOGE to fire at least 10% of park workers, maybe more. That’s almost 1,000 people fired of the 8100 jobs in Wyoming.

And each of these jobs, with their stable income, leads to other jobs in the community where the federal workers reside. So firing these workers will not only mean our national parks aren’t being maintained or kept safe, but will have an economic ripple effect across the entire state.

Many of the Musk/DOGE firings weren’t just ill-considered and bad, they were a major screw up.  An example of this was the firings of the people in the National Nuclear Safety Administration, part of the Department of Energy, who keep our nuclear stockpiles safe and secure.

Sources told CNN that DOGE staffers apparently did not realize that the agency oversees America’s nuclear weapons stockpile when the employees were fired Thursday. The terminations were quickly rescinded Friday, CNN reported

 

The workers were fired because “no one” had “taken any time to understand what we do and the importance of our work to the nation’s national security,” one source told CNN.

Energy Department scrambles to rehire nuclear bomb experts fired in major DOGE screw up

What’s worse, now the government can’t find the people to rehire them because they cancelled all their federal emails.

A memo sent to NNSA employees on Friday and obtained by NBC News read: “The termination letters for some NNSA probationary employees are being rescinded, but we do not have a good way to get in touch with those personnel.”

 

“Please work with your supervisors to send this information (once you get it) to people’s personal contact emails,” the memo added.

US government tries to rehire nuclear staff it fired days ago

The Musk/DOGE team also fired 50 first year members of the elite CDC Epidemic Intelligence Service, one of the premier disease research groups in the world. This, as humans infected with bird flu have been discovered in several new states this week.

Firing critically necessary people demonstrates how poorly managed this destructive action was. People fired were fired, unfired, and fired again. There’s been chaos across the government, which means our tax refunds aren’t being processed, our FEMA requests aren’t being answered, and any number of other essential government services aren’t being performed.

Also, by firing the newer members of government, we have lost a generational chance to bring in new ideas, new technologies, new training, as well as ensuring there are enough workers to actually perform the tasks and jobs delegated to them by Congress.

We know we don’t have enough migration judges, but we have even less now because Musk/DOGE just fired twenty.

The sheer stupidity of this mass, sudden firing is mind-boggling. It’s like Musk and his little gang of ijits didn’t spend ten minutes on trying to understand what a government is, and how it works. Musk somehow believes that what worked for Twitter—nothing more than one social media app among many—would work for the US Government.

And then forgot that whole sudden firing thing didn’t work that well for Twitter, either.

The federal employees fired were told to get out now;  in many cases, to clear out in 30 minutes. There’s no time to ensure a half finished job will be finished correctly, or let folks know where you’re at with a task. It will be days just to discover where people left off, and even more days (weeks or months) to finish the task, because there won’t be enough people to do all the work that needs to be done even when they finally recover from the chaos.

Just like Twitter. Except it won’t be a social media site going offline for a few hours every other day, it will be closed national parks, disease outbreaks, criminals who won’t get caught, risks to our national security, unpaid taxpayers, no support in a disaster, no home loans, no VA medical, and who knows, maybe we can no longer count on getting our Social Security checks, or that our doctors will get paid by Medicare.

The havoc happening right now will negatively impact on the government for years. The only silver lining is that when all of this crap really hits the fan, the country will have no doubt as who is to blame, and it certainly won’t be someone named Biden or Harris.

That’s probably the ultimate measure of Musk’s supposed ‘genius’: smart people don’t shoot themselves in the foot. Repeatedly.

Caricature of Musk courtesy DonkeyHoteyCC BY 2.0

Categories
Government

Dear Buddy Carter

Messages to my House Representative

Disregarding law, disregarding Congressional oversight, and disregarding just plain common sense, Trump is allowing Elon Musk and his kids to decimate our working government. Last night it was the CFPB.

This is the same organization that has helped consumers recover billions from financial services that have harmed us. This is also the same organization that would oversee Musk’s own entry into payment systems, which is likely why it was targeted.

Why does Musk have such power? Because the United States has been bought for a mere $280 million dollars by Musk, while Trump sits in the White House, trying to remember why he’s there. And Musk wants his money’s worth.

You, in Congress, could stop all this nonsense. You could, as a group, show a little bit of courage, as well as responsibility to the people who elected you to office. No, instead, you put your party over the people. You put Trump and Musk over the people.

All that matters now, to you, is what Trump/Musk want, they get. No matter how harmful to the people, no matter the lasting damage.

Instead of celebrating the 250th anniversary of our country, we get to watch it be destroyed.

More lawsuits will come from these actions, and the judges—appointed by both Republican and Democratic presidents—recognize what’s happening and are doing their best to enforce the rule of law…the same rule of law you just don’t give a damn about.

What did you say in your Sunday newsletter?

Together with Elon Musk, a business mastermind, President Trump is delivering on his promise to the American people that he will remove unnecessary government spending and save taxpayers money.

Save us money? The billions of dollars recovered for US taxpayers, that kind of money? The money to ensure our water is clean, our air breathable, that people aren’t harmed by defective products, to help farmers and small businesses, to ensure corporations don’t harm people, to help in disasters, to help kids go to school, to provide healthcare and financial stability for the nation’s retired community.

That money?

No, that money won’t be saved. The only money ‘saved’ will be tax cuts for you and your other rich friends.

Categories
Government

A bell that cannot be unrung

Among the many lawsuits against the Trump/Musk actions is one filed by the AFL/CIO and other labor organizations and unions against the Department of Labor for DOGE access to what should be confidential and private data.

In response, the government attempted to blow off the concerns by stating that DOGE folk are now employed by the DOL, but this is cold comfort when it’s obvious these people have an original allegiance to DOGE/Musk, and only a tenuous at best connection to the requirements of federal employment.

In the reply to the government response, the lawyers for the AFL/CIO highlight the real problem with the continue DOGE access at federal agencies.

Moreover, Defendants’ reassurance that all is well because DOGE1
personnel who have been granted broad access to the Department of Labor’s systems have been detailed to that agency is both cold comfort and legally insufficient. As a consequence of DOGE’s establishment as a free-floating component within the Executive Office of the President, it lacks the requisite authority to detail its personnel to federal agencies and, for the same reason, agencies may not receive those detailees.

 

Accordingly, the violations causing Plaintiffs irreparable harm, including under the Privacy Act, will persist, absent intervention from the Court.

These faux employees that Musk bullied into each department with Trump’s willing compliance have not undergone the regular reviews, with its checks and balances, for federal employment.  They have also not demonstrated a respect for law, particularly the stringent laws that guard the privacy and confidentiality of government systems.

And what harm is it to give DOGE this access?

Many of Plaintiffs’ members will be chilled from reporting legal violations by their employers and prevented from exercising their rights to seek the Department’s protections if they know that records memorializing their complaints may no longer be secure on Department servers (and, indeed, may be made freely available to individuals concurrently serving as executives of companies subject to Department enforcement).

Executives, such as Elon Musk, CEO of SpaceX, which had over 600 workplace injuries unconvered by a Reuters’ investigation, as reported to OSHA, an organization contained within the Department of Labor.

The response also notes another item of importance: that DOGE has no authority to employ people within the federal government. And federal departments have no authority to accept these people as employees.

Defendants argue that, because DOGE personnel at the Department have been “detailed” from DOGE to the Department, those individuals are functioning as employees of the Department and, accordingly, may lawfully perform Department functions and access Department systems. … But DOGE is not authorized to detail its personnel to the Department, or any federal agency, and the Department was not authorized to accept their services

So the employment of people such as Thomas Shedd, who I have written about previously, is inherently illegal, as is allowing them unlimited access to our data and our data systems.

As was noted in the response, once data has been exposed the damage is done and can’t be undone, “a bell that cannot be unrung.”

We shouldn’t have to sue to stop these people. The President’s first duty is to have a care for the American people. And Congress should be stepping up to prevent such atrocities, but evidently, it’s more concerned about $15 million dollars in condoms for the Taliban per Buddy Carter, my own Republican representative to the House.