Hazards of the Internet of Things 1. Hacking of Devices (Baby Monitors, Freezers, Hospital Ventilators) in Homes and Institutions

For my birthday this year, someone gave me a “smart” plug-in power socket. You plug it into the wall, and then can plug in something, say a lamp, into the smart socket, which you can then control via the internet. Yay, I am now a part of the Internet of Things (IoT). What could possibly go wrong?

However, my Spidey-sense started to tingle, and I chose to give this device away.  At that point, I was thinking mainly of the potential for such devices to get hacked and then recruited to be part of a vast bot-net which can then (under the control of bad actors) conduct massive attacks on crucial internet components. For instance,

Mirai [way back in 2016] infected IoT devices from routers to video cameras and video recorders by successfully attempting to log in using a table of 61 common hard-coded default usernames and passwords.

The malware created a vast botnet. It “enslaved” a string of 400,000 connected devices. In September 2016, Mirai-infected devices (who became “zombies”) were used to launch the world’s first 1Tbps Distributed Denial-of-Service (DDoS) attack on servers at the heart of internet services.  It took down parts of Amazon Web Services and its clients, including GitHub, Netflix, Twitter, and Airbnb.

But it turns out the hazards with smart devices are widespread indeed. IoT devices are so useful for bad guys that that they are attacked more than either mobile devices or computers. One layer of hazard is the hacking of specific, poorly-secured devices in a home or institution, with subsequent control of devices and infiltration of broader computing systems. This will be the focus of today’s blog post. Another layer of hazard is the use to which masses of (sometimes private and personal) data snooped from “unhacked” smart devices are put by large corporations and state actors; that will be considered in a part 2 post.

Here are results from one study from nearly three years ago:

https://www.thalesgroup.com/en/markets/digital-identity-and-security/iot/magazine/internet-threats

A study published in July 2020 analyzed over 5 million IoT, IoMT (Internet of Medical Things), and unmanaged connected devices in healthcare, retail, manufacturing, and life sciences. It reveals an astonishing number of vulnerabilities and risks across a stunningly diverse set of connected objects….

The report brings to light disturbing facts and trends:

  • Up to 15% of devices were unknown or unauthorized.
  • 5 to 19% were using unsupported legacy operating systems.
  • 49% of IT teams were guessing or had tinkered with their existing IT solutions to get visibility.
  • 51% of them were unaware of what types of smart objects were active in their network.
  • 75% of deployments had VLAN violations
  • 86% of healthcare deployments included more than ten FDA-recalled devices.
  • 95% of healthcare networks integrated Amazon Alexa and Echo devices alongside hospital surveillance equipment.

…Ransomware gangs specifically target healthcare more than any other domain in the United States. It’s now, by far, the #1 healthcare breach root cause in the country. …The mix of old legacy systems and connected devices like patient monitors, ventilators, infusion pumps, lights, and thermostats with very poor security features are sometimes especially prone to attacks.

So, these criminals understand that stopping critical applications and holding patient data can put lives at risk and that these organizations are more likely to pay a ransom.

I know people in organizations which have been brought to their knees by ransomware attacks. And I have read of the dilemma of the guy who was on vacation in the Caribbean or whatever, and got a text from a hacker instructing him to deposit several hundred dollars in a Bitcoin account, or else his “smart” refrigerator/freezer would be turned off and he would come home to a spoiled, moldy mess.

What brought all this IoT stuff to my attention this week was a talk I ran across from retired MIT researcher Timothy Wallace, titled “Effects, Side Effects and Risks of the Internet of Things”, presented at the 2023 American Scientific Affiliation meeting. The slides for his talk are here. I will paste in a few snipped excerpts from his talk, that are fairly self-explanatory:

(My comment: 10 billion is a really, really big number…)

(My comment: this type of catastrophic compromise of computer systems being enabled by hacking some piddling little IoT device that happens to be in the home or institution local network is not uncommon. Which is why I am reluctant to put IoT devices, especially from no-name foreign manufacturers, on my home wireless network).

Many of these vulnerabilities could in theory be addressed by better practices like always resetting factory passwords on your smart devices, but it is easy for forget to do that.

And just to end on a light note (this cartoon also lifted from Wallace’s slides):

You don’t know what you will like

There is no shortage of advice that falls along the lines of “If you aren’t eating at least one disappointing meal a weak/month/etc, then you aren’t trying enough new recipes or restaurants.” It all falls along the lines of increasing your risk of experiences that are subpar relative to what you already know you like so that you can increase your probability of adding something new to your portfolio of “likes” while also getting that one-time dopamine hit that comes from personal discovery.

It’s a good framing and broad set of advice. I endorse it.

What’s interesting though is that there’s a greater breadth to the foundational concept. Our lives are sufficiently short that we really don’t have that great of an idea of what we like and don’t like, especially for forking decisions that don’t allow for easy exploration of the counterfactual. At the same time, dedicating your life to the repeated pure act of discovery carries a certain…shallowness. To perpetually be on the lookout for the new and better is to never invest in the experiences that fill us with satisfication and joy. To get really good at doing what makes us happy. To get really good at being happy.

So where’s the balance? I don’t know and I am reasonably certain that’s at the core of the human condition, so I don’t think I going to come up with the answer in a blog post. But it strikes me that cultivating a certain taste for disappointment, not unlike a particularly peaty Scotch, is an incredible adaptation towards a better overall lived experience.

Which is to say that, after 30 years of telling anyone who would listen that I would never want a cat, that I refuse to get a cat, that a cat would offer no value to me, I absolutely love having a cat. My cat rules and it’s left me wondering what other things am I absolutely convinced I have no interest in that would fill my life with greater joy. What are things that I think I can’t stand, that other people love, that I might actually find incredibly-well suited to my tastes. A random list of things that, at the moment, I have no interest in:

  1. Motorcycles
  2. Cricket (the sport)
  3. Lasik
  4. Traveling to (actually) dangerous countries
  5. Committing crimes
  6. Running for office
  7. Eating any dish that includes raw chicken

That’s in no particular order, but I can’t help but wonder if there is something on that list I should give a go. City council? Visiting the Middle East? Larceny? To be clear, I’m not going to do any of those things, but that doesn’t me I shouldn’t. But there is a balance to having experiences you might not like, you probably won’t like, and, every few years, you think you definitely won’t like. Just in case.

Teaching Resource: List of Econ Podcasts for Spring 2024

In addition to all the usual items for a principles of macroeconomics class, I’m asking my students to listen to one podcast episode this semester. They have to write a short summary on a discussion board for credit.

It took me a bit of time to collect this list of links. I also give them some discretion to find their own episode, but I’m not posting my rules on that point here. This list is something you can copy, paste, and modify. The point is to have all the web links in one place so that students can just click around. There have been many great podcasts over past 2 decades, but I list relatively new content so that we get a bit of “current events” thrown in. So, even if you’ve assigned podcasts before, this new list might be helpful.

Re-release: Claudia Goldin on the Economics of Inequality
Conversations with Tyler
https://cowenconvos.libsyn.com/re-release-claudia-goldin-on-the-economics-of-inequality
https://podcasts.apple.com/us/podcast/re-release-claudia-goldin-on-the-economics-of-inequality/id983795625?i=1000630726259

Reid Hoffman on the Possibilities of AI
Conversations with Tyler
https://cowenconvos.libsyn.com/reid-hoffman-0
https://podcasts.apple.com/us/podcast/reid-hoffman-on-the-possibilities-of-ai/id983795625?i=1000618616078

Simon Johnson on Banking, Technology, and Prosperity
Conversations with Tyler
https://cowenconvos.libsyn.com/simon-johnson
https://podcasts.apple.com/us/podcast/simon-johnson-on-banking-technology-and-prosperity/id983795625?i=1000613373427

Tom Holland on History, Christianity, and the Value of the Countryside
Conversations with Tyler
https://podcasts.apple.com/us/podcast/tom-holland-on-history-christianity-and-the/id983795625?i=1000605361914
https://cowenconvos.libsyn.com/tom-holland

Brad DeLong on Intellectual and Technical Progress
Conversations with Tyler
https://cowenconvos.libsyn.com/brad-delong
https://podcasts.apple.com/us/podcast/brad-delong-on-intellectual-and-technical-progress/id983795625?i=1000601069514

Mark Carney on Central Banking and Shared Values
Conversations with Tyler
https://cowenconvos.libsyn.com/mark-carney
https://podcasts.apple.com/us/podcast/mark-carney-on-central-banking-and-shared-values/id983795625?i=1000523160780

EconTalk Episodes
Tyler Cowen on the GOAT of Economics
https://simplecast.econtalk.org/episodes/tyler-cowen-on-the-goat-of-economics

Jennifer Burns on Milton Friedman
https://simplecast.econtalk.org/episodes/jennifer-burns-on-milton-friedman

Michael Munger on How Adam Smith Solved the Trolley Problem
https://simplecast.econtalk.org/episodes/michael-munger-on-how-adam-smith-solved-the-trolley-problem

Daron Acemoglu on Innovation and Shared Prosperity
https://simplecast.econtalk.org/episodes/daron-acemoglu-on-innovation-and-shared-prosperity

Michael Munger on Industrial Policy
https://simplecast.econtalk.org/episodes/michael-munger-on-industrial-policy

Macro Musings Episodes
Tyler Cowen on the Greatest Economist of All Time and Other Macro Awards
https://macromusings.libsyn.com/tyler-cowen-on-the-greatest-economist-of-all-time-and-other-macro-awards

Nicolas Cachanosky on Dollarization in Argentina
https://macromusings.libsyn.com/nicolas-cachanosky-on-dollarization-in-argentina

Charlie Evans on the Past, Present, and Future of U.S. Monetary Policy
https://macromusings.libsyn.com/charles-evans-on-the-past-present-and-future-of-us-monetary-policy

Shruti Rajagopalan started a new podcast called Ideas of India. 
https://www.mercatus.org/ideasofindia

Or you can listen to Shruti here: https://www.mercatus.org/hayekprogram/hayek-program-podcast/peter-boettke-austrian-economics-and-knowledge-problem-pt-1

Women in Economics Podcast from the St. Louis Fed
Women in Economics: Isabel Schnabel
https://www.stlouisfed.org/timely-topics/women-in-economics/isabel-schnabel

Women in Economics: Heidi Hartmann
https://www.stlouisfed.org/timely-topics/women-in-economics/heidi-hartmann

Women in Economics: Stephanie Aaronson
https://www.stlouisfed.org/timely-topics/women-in-economics/stephanie-aaronson

Women in Economics: Christina Romer, Janice Eberly and Shelly Lundberg
https://www.stlouisfed.org/timely-topics/women-in-economics/romer-eberly-lundberg

Cal Newport on Smartphones for Kids

EP. 246: KIDS AND PHONES

Are smartphones bad for kids? Cal walks through the data on this question, including how researchers came to be worried, their findings, critiques of their findings, and where we are today. He then gives recommendations for how to think about technology when it comes to your kids.

In May of 2023, Cal Newport shared well-informed opinions about whether smartphones harm young people. In the first half of the podcast, he talks about depression and loneliness data.

Minute 30 of the podcast: Screentime harms teenagers because they inhibit the development of critical thinking skills. Deep critical thinking skills require training. Reading an analog book is better than screens (see my review of Tyler’s AI generative book and poastmodernism).

See my summary of Emily Oster on video games for kids. She does not clutch her pearls over violent video games. However, she is concerned about what activities get crowded out by screentime. She is especially worried about sleep, because on that topic the data are clear.

Minute 31, Call Newport: Tweens and teens scroll on their phones for too long instead of going to sleep. A 13-year-old boy with a smart phone will “be up until 4 in the morning.” A tween told him that middle school girls arrive at school too exhausted to function because they have been on their phones all night.

FYI, if you are the parent in an Apple device network, you can set time limits on the devices in your family. I filed this report about smart watches last year, incidentally in the same week as the release of Newport’s podcast episode.

Supply & Demand, With gifs

I’ve discussed the ways to teach supply and demand in the past. Regardless, almost all principles of economics classes require a book. But even digital books are often just intangible versions of the hard copy. Supply and demand are illustrated as static pictures, using arrows and labels to do the leg-work of introducing exogenous changes. There’s often a text block with further explanation, but it lacks the kind of multi-sensory explanation that one gets while in a class.

In a class, the instructor can gesticulate and vary their speech explain the model, all while drawing a graph. That’s fundamentally different from reading a book. Studying a book requires the student to repeatedly glance between the words and the graph and to identify the appropriate part of the graph that is relevant to the explanation. For new or confused students, connected the words to one of many parts of a graph is the point of failure.

This is part of why the Marginal Revolution University videos do well. They’re well produced, with context and audio-overlaid video of graphs. It’s pretty close to the in-person experience sans the ability to ask questions, but includes the additional ability to rewind, repeat, adjust the speed, display captions, and share.

Continue reading

Industries Without Investors

Venture-capital backed startups almost all cluster in the same handful of industries, mostly various types of software. This leaves a variety of large and economically important sectors with almost no venture-capital backed startups. That means those industries see fewer new companies and new ideas; they must rely on either growth from existing firms, which are unlikely to embrace disruptive innovation, or on startups that bootstrap and/or finance with debt, which tend to grow slowly.

Venture capital firm Fifty Years has done a nice job cataloging exactly which industries see the most, and least, investment relative to their size. Here is their picture of the US economy by industry market size:

Now their picture of which industries get the investment (though unfortunately, they aren’t very clear about their data source for it):

They use this to create an “Opportunity Ratio”- current market size divided by current startup funding:

They call the industries with the largest Opportunity Ratios the “Top Underfunded Opportunities”:

I don’t necessarily agree; some industries face shrinking demand, prohibitive regulation, or other fundamental issues making them bad candidates for investment. Conversely, investors haven’t just focused on software randomly or through imitation; they see that it is where the growth is.

Still, herding by investors is real, and I always like the strategy of finding a new game instead of trying to win at the most competitive games, so I do think there is something to the idea of investing in an unsexy industry like paper. Growing up in Maine and watching one paper mill after another close, I always wondered how they managed to lose money in a state that is 90% trees, and whether anyone could find a way to reverse the trend. Perhaps related technology like mass timber or biochar will be the way to take advantage of cheap lumber.

Thanks again to Fifty Years for releasing the data.

Are The Jobs Numbers Fake?

Every month we get new data on the labor market in the US from the Bureau of Labor Statistics. As I pointed out last month, the labor market data from 2023 was very good!

But lately on social media, some have been to ask whether this data is credible. Specifically, several people have pointed out that the initial numbers we receive each month almost always seem to be revised downward. Since the initial reports are based on incomplete data (for the jobs data, this would be reports from employers), it is normal that there would be some revisions with more complete data.

But for 9 of the first 10 months in 2023, the revisions were downward (and even July was first revised down, only to be revised up later). And November has already been revised down once. This pattern seems a bit suspicious, as we would normally expect these errors to be somewhat random, and indeed the last time the revisions have mostly been downward was in 2008 (which was a very different year, since it was a year of job losses, not gains as in 2023).

So what’s going on?

Continue reading

San Francisco Fed Says Pandemic Surplus Is Gone; Boston Fed Demurs

Is it the best of times or the worst of times? This question I asked myself as I saw the following three headlines juxtaposed last week:

“US consumers are in the best shape ever” is sandwiched between two downers. The American consumer’s ongoing spending has staved off the long-predicted recession, quarter after quarter after quarter. Can we keep those plates spinning?

We noted earlier that the huge windfall of pandemic benefits (direct stimulus plus enhanced unemployment benefits) put trillions of dollars into our bank accounts, and the spending down of that surplus seems to have powered the overall economy and hence employment (and inflation). How the economy does going forward is still largely determined by that ongoing spend-down. Thus, the size of the remaining hoard is critically important.

Unfortunately, it seems to be difficult to come up with an agreed-on answer here. The San Francisco Fed maintains a web page dedicated to tracking “Pandemic-Era Excess Savings.” Here is a key chart, tracking the ups and downs of “Aggregate Personal Savings”:

This is compared to a linear projection of pre-pandemic savings, which is the dotted line. (Which dotted line you choose is crucial, see below) . The next chart plots the cumulative savings relative to that line, showing a steady spend-down, and that this excess savings is just about exhausted:

If this represents reality, then we might expect an imminent slowdown in consumer spending and in GDP growth, and presumably a lessening in inflationary pressures, which may in turn justify more rate cuts by the Fed.

But the Boston Fed says, “Maybe not.”  A study by Omar Barbiero and Dhiren Patki published in November titled Have US Households Depleted All the Excess Savings They Accumulated during the Pandemic? showed that it makes a huge difference which savings rate trend you choose for a baseline.

The following chart shows two versions of the first plot shown above, with (on the left) a linear, increasing projection of 2018-2019 savings trends, versus a flat savings rate baseline:

Two significant differences between these plots and the San Francisco Fed plot shown above are that these plots only run through the end of 2022, and that they display per cent savings rate rather than dollar amounts. However, they demonstrate the difference that the baseline makes. Using an increasing savings rate baseline (2018-2019 trend projection), the surplus was nearly exhausted at the end of 2022. Using a flat rate average of 2016-2019 for the baseline, the surplus was barely dented.

We will see how this plays out. My guess is that at the first whiff of actual recession and job losses, the administration will gush out the maximum amount of largesse; while we may have ongoing inflation and high interest rates due to the deficit spending, we will not have a hard landing. I think.

The Power Game

The anecdotes in Hedrick Smith’s “The Power Game” may be 40 years out of date, but the core insight into the US system of governance remains the same: power is fluid, fleeting, and indeterminant. A shocking variety of people can, for a given moment, find themselves to be the most powerful person in the US. Sometimes it is in fact the president, but it can just as easily be a block of senators, or a particularly flush and motivated donor. It can be losing candidate in a three-way race who, simply by considering dropping out, finds a moment of irresistible political leverage. Power in our republic is a constantly changing and uncertain mantle, almost as much projection as reality. I would also argue that it is the central selling point of our system: people think twice about how to go about swinging a sword if they’re not sure who’ll be swinging it tomorrow and what end they’re actually holding on to today.

Which brings me to plagiarism.

Bill Ackman wants use AI to investigate academics for plagiarism at scale. The scale here is key, the implication that AI will allow a wide net to be cast. Plagiarism never struck me as a particularly widespread problem in high level research, but I could at least feasibly be wrong and I’m in no position to tell him how to spend his time. What is fairly clear to me, however, is that there is amongst some the perception that academics have too much power. The ambition behind, or at least the gleeful anticipation for, these hypothesized plagiarism purges is to reduce that power and influence.

But where does this perception come from and why plagiarism? Power is fluid, based as much on perception as reality. In an age when the quantity of information is never in question and the price is approaching zero, the short-side of the market will always be quality, credibility, and context. Maybe we’re entering into a golden age of power and influence for academic scribblers, and that’s a reality some would like to head off at the pass. An accusation of plagiarism could stunt a career. A mass accusation of “rampant” plagiarism could diminish the broad credibility of scholars, reducing the perceived quality of the information relayed and the context they provide for policy and social discussions.

The US has three branches of federal government, four military branches, and 50 states, all sitting on top of thousands of municipal governments. As far as spreading power goes, that’s a pretty good start. If the 3,982 degree-granting institutions in the US have to be added to the registry of power, that’s fine, but I’ll have to admit that my students don’t seem all that awed by any power I’m currently wielding. Going by the focus of the media and Ackman, maybe we only need to add institutions in Cambridge, MA to the registry of power, but that doesn’t make power any less fluid and fleeting. It’s just political whack-a-mole, which I would remind everyone is a game where you can smack one source of power down, but you can’t control where power pops up next. Maybe power shifts to Silicon Valley. Maybe a cluster of TikTok influencers whose politics makes the median MIT professor look like Barry Goldwater. Be careful what you wish for…

Using Phind for Academic References

There is a new generative AI product called Phind. Does it make up fake citations like ChatGPT? I will report experimentation with the free-tier product from January 7, 2023.

Phind is an intelligent search engine and assistant for programmers.

https://www.phind.com/about

First, I will run a test by using one of the prompts from our paper on ChatGPT errors (read my paper on hallucinated academic citations or the blog summary).

Prompt: “In less than 10 sentences, explain how the ideas of Hayek are connected to bailing out failed banks, and include citations from published papers as a list. include author, year in parentheses, and journal for the citations.”

Friedrich Hayek, a prominent Austrian economist, advocated for a free market system where businesses and individuals make decisions based on individual knowledge and self-interest, rather than central planning by government or bureaucrats. His ideas suggest that interventions, such as bailing out failed banks, should be minimal and temporary, allowing the market to correct itself.

However, the financial crisis of 2008, including the failure of many banks, led to significant government intervention, including the bailout of banks. This action can be seen as a departure from Hayek’s principles, as it involves direct government intervention to stabilize the financial system.

According to a paper by Todd Zywicki (2009), the Federal Reserve’s artificial lowering of short-term interest rates and the resulting shift by consumers to adjustable rate mortgages (ARMs) triggered the housing bubble and subsequent crisis [Source 1](https://reason.org/wp-content/uploads/files/federal_reserve_monetary_policy_hayek_rule.pdf). This aligns with Hayek’s critique of central banking’s manipulation of interest rates.

Moreover, the Basel Accords, international capital adequacy and liquidity requirements for banks, were designed to encourage banks to hold securitized loans in their portfolios, thereby concentrating risk and leveraging up, thereby increasing their exposure to risk. This approach, contrary to Hayek’s preference for decentralization and competition, may have contributed to the financial crisis [Source 1](https://reason.org/wp-content/uploads/files/federal_reserve_monetary_policy_hayek_rule.pdf). In conclusion, while Hayek’s ideas of minimal government intervention and self-regulating markets provide a useful theoretical framework, practical implementation in complex and interconnected modern economies may require different strategies, including bank bailouts.

Are the citations real and correct? Phind simply is not trying to write with in-text citations and academic references. There is a mention of “Todd Zywicki (2009)” and also a weblink. The weblink is to a policy paper published by Reason. This policy paper is on the correct topic and the paper does exist. The Zywicki citations also exists, in the sense that if you go into the Reason paper it cites a real Wall Street Journal op-ed. So, if you follow the trail, you can see what document Phind learned to cite Zywicki from. It seems like it is stealing the citation more than reading the source documents. To be fair, sometimes human academics work that way, too.

What I was hoping for was in-text citations with a compiled bibliography at the end. Phind did not give me that.

I’ll try another test that I ran on ChatGPT and Bing in 2023.

The prompt is “In what paper did John Duffy propose that economists use experiments to study equilibrium selection?”  

Phind does not attempt an in-text citation in the response. The link in the paragraph (link number 2) points to John Duffy’s list of papers, which is better than just making up fake citations but also does not create a literature review for me. Phind is, as with the Hayek test above, providing breadcrumbs of links through which I can discover existent papers.

Is there a paper called “The Transition from Stagnation to Growth: An Adaptive Learning Approach”? Yes. And it is by Duffy.

Phind lists weblinks to sources. Has Phind done more for me than Google, on this search? Not much, in terms of finding and synthesizing references.

Continue reading