Perspective on Risk - March 23, 2024
Follow-up To The Climate Risk Perspectives; Volt Typhoon; Less Serious Stuff
Back from a nice trip to the Low Country (Charleston and Savannah). She-crab soup is one of my favorite things, and I think I had it four days in a row. There’s a lot to discuss in the AI/LLM space, but synthesizing that will take some time. So for now …
Follow-up To The Climate Risk Perspectives
While away, I got a number of behind-the-scenes comments and questions on the last Perspective where I updated the climate risk information. Most hit me with the usual fatalistic:
“So What Should We Do About It”
Well, here are a few things that I think are possible and that we should do.
Price the Externality. We know the climate-related costs are not incorporated in the price of fossil fuels. Because of this, we are using more than we would if the price reflected all costs (a Tragedy of the Commons scenario). At a minimum, we should have a price that fully reflects the externality cost (ideally through a market, though a tax/levy is a 2nd best solution). Ideally any market would tie the available emissions to the planned path needed to meet the climate goals. I actually don’t care how you use the money; creating the proper incentive to reduce demand is the important part. Interestingly, the global shipping industry is now considering such an approach.1
Eliminate single-use plastics. While not a fan of regulation, we should consider eliminating single-use plastics. This contributes about 3% of GHG emissions.
Cash for clunkers. Pay up for the oldest, least efficient automobiles. Get them off the road. Probably best to just pay cash, but one could also consider vouchers towards new hybrids or EVs. Claude-2 estimated that this would be a quick 15% drop in vehicle emissions.2
Consider geoengineering approaches. Part of our current problem is that we have been effective at eliminating the use of high-sulfur bunker fuel to power ships. Sulfur emissions suppressed the warming of greenhouse gases. It is within our technical capabilities to introduce sulfur or other particulates into the atmosphere. Unfortunately, an initiative to test this approach was just cancelled.3
Continue to push for renewables. I’ll be putting solar on my new house. With tax incentives I will recoup my costs in 3-4 years, very high and certain ROI, and if I buy an EV or plug-in hybrid I can eliminate my gasoline bill. I’m also looking at how I can put solar on the flat roof of the food pantry where I volunteer.4
Serious Stuff - Volt Typhoon
PRC STATE-SPONSORED CYBER ACTIVITY: ACTIONS FOR CRITICAL INFRASTRUCTURE LEADERS (CISA)
This fact sheet provides an overview for executive leaders on the urgent risk posed by People’s Republic of China (PRC) state-sponsored cyber actors known as “Volt Typhoon.” CISA—along with the National Security Agency (NSA), the Federal Bureau of Investigation (FBI), and other U.S. government and international partners1—released a major advisory on Feb. 7, 2024, in which the U.S. authoring agencies warned cybersecurity defenders that Volt Typhoon has been pre-positioning themselves on U.S. critical infrastructure organizations’ networks to enable disruption or destruction of critical services in the event of increased geopolitical tensions and/or military conflict with the United States and its allies. This is a critical business risk for every organization in the United States and allied countries.
Less Serious Stuff
To outperform, hire poor, headbanging women
Testosterone Causes Bubbles
The Bull of Wall Street: Experimental Analysis of Testosterone and Asset Trading
Using both aggregated and individual trading data, we find that testosterone administration generated larger and longer-lasting bubbles by causing high bids and the slow incorporation of the asset’s fundamental value.
To All Those Who Criticized My Music Playing
I was known to bang out some tunes on speakers in the office, rather than use headphones. It was all for a good reason: AC/DC Enhances Productivity
Effect of Genre and amplitude of music during laparoscopic surgery
Novice surgeons underwent a proficiency-based laparoscopic training curriculum. Participants were required to perform these tasks under three conditions: no music, with music in medium volume (45-50 dB) and in high volume (65-70 dB). Soft rock by the Beatles and hard rock by AC/DC were played.
With hard rock in medium volume, participants were faster performing precision cutting (139.4 vs. 235.8, P = 0.0009) compared to without music. Both balloon preparation and precision cutting were performed more rapidly (227.3 vs. 181.4, P = 0.003, 139.4 vs. 114.0, P < 0.0001) and the accuracy was maintained. Hard rock in high volume also resulted in increased speed (366.7 vs. 295.5, P < 0.0001) compared to without music. Thereby, the total scores of participants were enhanced (516.5 vs. 437.1, P = 0.002).
For those about to rock, we salute you.
Hire Poor
Family Descent as a Signal of Managerial Quality: Evidence from Mutual Funds
We find that managers from poor families deliver higher alphas than managers from rich families.
Managers born rich are more likely to be promoted, while those born poor are promoted only if they outperform.
Translating Words To Probabilities
Bayesians like to think in probabilities. The rest of the world uses words. Words like “likely,” “unlikely,” doubtful,” “almost certainly,” and “rare.” It is useful to know what the typical person assesses the probability at when using such loose phrases. I’ve frequently used some version of this chart:
Michael Maubisson pointed out that an old HBR article he coauthored, If You Say Something Is “Likely,” How Likely Do People Think It Is? (HBR), noted that there are some differences between men and women in how they use certain phrases:
We also found that men and women see some probabilistic words differently. As the table below shows, women tend to place higher probabilities on ambiguous words and phrases such as “maybe,” “possibly,” and “might happen.” Here again, we see that “possible” and its variations particularly invite misinterpretation. This result is consistent with analysis by the data science team at Quora, a site where users ask and answer questions. That team found that women use uncertain words and phrases more often than men do, even when they are just as confident.
The authors also noted that there is apparently a cultural difference when people use the term “slam dunk”
On average, the native English speakers interpreted the phrase [slam dunk] as indicating a 93% probability, whereas the nonnative speakers put the figure at 81%. This result offers a warning to avoid culturally biased phrases in general and sports metaphors in particular when you’re trying to be clear.
World’s First Global CO2 Charge Inches Closer at London Meetings (Bloomberg)
The International Maritime Organization — which regulates shipping worldwide — inched closer toward such a [green house gas] levy at talks held in London this week. The United Nations agency plans to finalize the detail of the measure next year, and have it introduced in 2027.
Countries including the Marshall Islands — the flag state for thousands of vessels — earlier submitted a proposal for a minimum emissions charge of $150 per ton of CO2-equivalent, which would add hundreds of dollars to shippers’ fuel bills for every ton of oil they burn. Others, including European Union nations, Canada and China have submitted separate documents discussing GHG pricing.
I asked Claude-2 “How much would we reduce automobile carbon emissions if we replaced the least efficient quarter of vehicles with EVs or hybrids?“. It answered as follows:
The exact reduction in carbon emissions from replacing the least efficient quarter of vehicles with EVs or hybrids would depend on various factors such as the specific vehicles being replaced, the energy mix used to generate electricity for EVs, and the driving habits of vehicle owners. However, we can make a rough estimate based on some assumptions.
Assumptions:
Passenger vehicles account for about 60% of transportation-related greenhouse gas emissions in the U.S.
The least efficient quarter of vehicles are responsible for a disproportionately high share of emissions, say 40% of passenger vehicle emissions.
EVs and hybrids emit 50-70% less carbon dioxide than the average conventional vehicle, depending on the energy mix.
Under these assumptions, if we replaced the least efficient 25% of vehicles with EVs or hybrids, the reduction in total passenger vehicle emissions would be:
40% (emissions from least efficient vehicles) × 50-70% (emissions reduction per vehicle) = 20-28% reduction in total passenger vehicle emissions
Since passenger vehicles account for 60% of transportation emissions, this would translate to a reduction of:
60% (share of transportation emissions) × 20-28% (reduction in passenger vehicle emissions) = 12-17% reduction in total transportation-related emissions
This is a significant reduction, but keep in mind that it is a rough estimate based on simplified assumptions. The actual impact would depend on the specific implementation of such a program and the broader energy context.
We need to talk about carbon removal (FT)
Harvard has halted its long-planned atmospheric geoengineering experiment (MIT Technology Review)
Harvard researchers have ceased a long-running effort to conduct a small geoengineering experiment in the stratosphere, following repeated delays and public criticism.
The plan for the Harvard experiments was to launch a high-altitude balloon, equipped with propellers and sensors, that could release a few kilograms of calcium carbonate, sulfuric acid or other materials high above the planet.
This seems like a no-brainer. Simultaneously reduces non-profit operating costs while moving towards our renewable goals.
You didn't mention nuclear energy as a means for generating electricity. Without a stable source of electricity, EVs are rendered useless. The same is true for use of electricity for homes and buildings. As for safety of nuclear reactors, keep in mind that Pakistan has operated nuclear power plants for the past 30 years safely, despite the presence of the Taliban, ISIS, and Al-Qaeda. The US shouldn't lag behind Pakistan.
What about disposing of nuclear waste? It is no more formidable a problem than disposing of solar panels and EV batteries. Neither of the latter two can be recycled. Uranium mining can be done safely and domestically. The lithium, cadmium, and assorted rare earth element ores required for solar panels and EV batteries are environmentally dangerous (high toxicity to human miners) and are sourced primarily from China or poor African countries who are becoming vassal states to Chinese overseas investment. I think your hybrid vehicle suggestion is good! Eliminating single-use plastics, especially for retail/consumers is an excellent idea for both the climate and human health. I would love to see that happen!
I am unsurprised about the AC/DC boost to productivity findings. It is part of my own lived experience!
Thank you for the heads up about Volt Typhoon. Scary name too.
Quora you say? I am there, have been there since 2010. It has kind of degraded though. I use the sobriquet Math Troll on Quora, if you ever want to stop by and say hello.
EDIT: That deadweight loss triangle looks odd. I have always seen it flipped by 180 degrees. I tried to include a link from the CFA Institute but Substack comments wouldn't allow it. I tried to figure out why your triangle is differently oriented than the Harberger's triangle (due to the loss from government interference in perfect markets, or due to monopoly pricing power, etc.) Could you explain please?