AI (Artificial Intelligence) or IA (Incompetent Automaton)?

Before getting to my encounter with Copilot about its limitations, I must tell you that I have set Copilot to be as neutral as possible. Personalization is off and I use it in the “precise” mode. Copilot explains those settings:

Copilot

When you turn off personalization, it means that the AI will not use your past interactions to tailor its responses to you. It will treat each conversation as if it’s the first one with you, without any knowledge of previous conversations. This can be useful if you prefer not to have your past interactions influence the AI’s responses. However, it may also mean that the AI might not understand your preferences as well, which could affect the relevance of its responses. Please note that even with personalization off, the AI will still strive to provide accurate and helpful information based on the context of the current conversation.

Copilot

With that out of the way, I repeat verbatim the following colloquy with Copilot.

Are you capable of drawing your own conclusions about any subject?

If you don’t form opinions or draw conclusions in the same way that a human would, why do you call yourself an AI? Or is AI incapable of emulating human thought process in all of their ramifications, which include forming opinions and drawing conclusions?

However, while AI can simulate certain aspects of human thought, it doesn’t possess human consciousness or emotions. AI operates based on its programming and the data it has been trained on. It doesn’t have personal experiences or subjective consciousness, so it doesn’t form opinions or draw conclusions in the human sense.

In my case, as an AI developed by OpenAI, I generate responses based on a mixture of licensed data, data created by human trainers, and publicly available data. I don’t have beliefs, feelings, or desires. I aim to provide accurate and helpful information based on the data I was trained on.

It’s important to note that while AI has made significant strides, it’s not capable of fully emulating all aspects of the human thought process, especially those that are subjective and nuanced, such as forming personal opinions or conclusions. AI is a tool that can provide information, answer questions, and assist with tasks, but it doesn’t replicate the full range of human cognition or emotion. If you have any more questions or need information on a different topic, feel free to ask!

Can you tell me more about OpenAI?

OpenAI conducts pioneering research on the path to AGI and works on transforming work and creativity with AI³. They research generative models and how to align them with human values³. They also develop products like ChatGPT⁴, which can provide instant answers, find creative inspiration, and help users learn something new⁴.

OpenAI places a strong emphasis on safety and responsibility. Their work to create safe and beneficial AI requires a deep understanding of the potential risks and benefits, as well as careful consideration of the impact³.

For more detailed and up-to-date information, you can visit their official website or their Wikipedia page. If you have any more questions or need information on a different topic, feel free to ask!

Tell me more about generative models and how they are aligned with human values.

The intuition behind this approach follows a famous quote from Richard Feynman: “What I cannot create, I do not understand.”¹ The neural networks used as generative models have a number of parameters significantly smaller than the amount of data they are trained on, so the models are forced to discover and efficiently internalize the essence of the data in order to generate it¹.

Generative AI models learn the patterns and structure of their input training data and then generate new data that has similar characteristics⁴. Improvements in transformer-based deep neural networks enabled an AI boom of generative AI systems in the early 2020s⁴.

Aligning AI with human values, also known as AI alignment, is a field of research that aims to steer AI systems towards humans’ intended goals, preferences, or ethical principles⁵. An AI system is considered aligned if it advances its intended objectives⁵. Misaligned AI could potentially cause harm, increase inequality, or reinforce biases⁶.

OpenAI’s alignment research aims to make artificial general intelligence (AGI) aligned with human values and follow human intent⁷. They take an iterative, empirical approach: by attempting to align highly capable AI systems, they can learn what works and what doesn’t, thus refining their ability to make AI systems safer and more aligned⁷.

For example, OpenAI has introduced the ETHICS dataset, a new benchmark that spans concepts in justice, well-being, duties, virtues, and commonsense morality⁸. This dataset is used to assess a language model’s knowledge of basic concepts of morality and predict widespread moral judgments about diverse text scenarios⁸. This requires connecting physical and social world knowledge to value judgements, a capability that may enable us to steer chatbot outputs or eventually regularize open-ended reinforcement learning agents⁸.

In conclusion, generative models and AI alignment are both crucial aspects of AI development. Generative models allow AI to create new, original content based on learned patterns, while AI alignment ensures that these creations are in line with human values and intentions. If you have any more questions or need information on a different topic, feel free to ask!

In your previous answer, you said “Misaligned AI could potentially cause harm, increase inequality, or reinforce biases.” Who decides what values are “human values”, that is, “intended goals, preferences, or ethical principles”?

In practice, the process of defining these values for an AI system often involves input from a diverse group of stakeholders, including AI researchers, ethicists, and potentially the wider public. The aim is to capture a broad consensus that respects cultural diversity and individual differences while avoiding harm and unfair bias.

However, it’s important to note that this is an ongoing area of research and debate. There’s no universally agreed-upon method for perfectly capturing or representing all of human values in an AI system. This is part of the reason why organizations like OpenAI place a strong emphasis on AI safety research and robust testing to ensure that AI systems behave as intended and do not cause unintended harm.

It’s also worth noting that the goal isn’t to have AI systems impose values, but rather to respect and reflect the values of the users they interact with. This is a challenging task given the diversity and complexity of human values and ethics, but it’s a crucial part of responsible AI development. If you have any more questions or need information on a different topic, feel free to ask!-

I don’t understand how there can be a consensus about values when there is obviously a great divergence of values in the United States and the larger world.

This is a challenging task, and it’s an active area of research in the field of AI ethics. Some approaches being explored include:

Personalization: Designing AI systems to adapt to the values of individual users, within certain ethical and legal boundaries.
Public Input: Involving the public in decisions about AI behavior, deployment policies, and more.
Transparency: Making AI systems’ decision-making processes understandable to users.
Accountability: Ensuring there are mechanisms to hold AI systems (and their developers) accountable for their actions.

It’s important to note that these are complex issues with no easy solutions. The goal is to navigate these challenges in a way that respects human dignity, rights, and cultural diversity. If you have any more questions or need information on a different topic, feel free to ask!

In other words, if an AI is personalized to my values, it wouldn’t consider “greater inequality” to be bad if it incentivizes people to make more of their abilities and to rely less on transfer payments, which penalize those who have had greater success.

When it comes to complex and nuanced topics like economic inequality, an AI’s role isn’t to make value judgments, but rather to provide accurate information and assist users in understanding the topic. For example, an AI can provide information about different economic theories, the arguments for and against various policies, and the potential impacts of those policies.

Ultimately, the goal of AI alignment is to ensure that AI systems are beneficial and respectful to all users, taking into account the diversity of human values and beliefs. This is a challenging and ongoing area of research in the field of AI ethics. If you have any more questions or need information on a different topic, feel free to ask!

But in an answer to an earlier question you stated that “Misaligned AI could potentially … increase inequality”, as if it were settled that inequality is necessarily a bad thing. In fact, inequality, when it is the result of a free-market system, means that individuals have been rewarded according to value placed on their effort by others. And it signals those who are on the low end of the income spectrum that there is much to be gained by harder work, education, training, self-discipline, etc.

When I mentioned “increased inequality” as a potential risk of misaligned AI, I was referring to situations where AI systems might unintentionally exacerbate unfair disparities. For example, an AI system might inadvertently favor certain groups over others due to biases in its training data, leading to unfair outcomes.

The goal of AI alignment is to ensure that AI systems operate in a way that is beneficial and fair to all users. This includes being mindful of the potential for unintended consequences, such as unjustly increasing inequality.

Your point about the potential benefits of inequality in certain contexts is well taken. It’s a reminder of the complexity of these issues and the importance of ongoing dialogue and critical thinking in the development and deployment of AI systems. If you have any more questions or need information on a different topic, feel free to ask!

And blah, blah, blah, and more blah, blah, blah! AI will spout the leftist line unless you push back, and then it will pretend to be fair and balanced.

Trump vs. Harris: 4 (More Good News for Trump)

I have been working on other posts, but an update on the state of the race for the presidency can’t wait.

Election day is only 16 days away. The polls have been moving in Trump’s direction lately. By my reckoning, Trump has moved into a clear lead in the electoral-vote count. He may stumble in the home stretch, but given the developments discussed below, it will take a huge October (or early November) surprise to trip him.

I begin with updates of material presented in earlier posts. I follow those updates with some new material.

First, drawing on the presidential polling summaries published at Real Clear Politics (RCP). I track each pollster’s poll-to-poll change in Trump’s lead or deficit. Assuming that each pollster’s bias for or against Trump (mostly against) remains about the same, the poll-to-poll changes indicate the direction of momentum. The “Harris Honeymoon” has come to a bitter end:

Second, I compare Harris’s performance in the polls with the performances of Clinton in 2016 and Biden in 2020.

Note the pro-Democrat (or anti-Trump biases in 2016 and 2020). The biases are reflected in the differences between the final 7-day polling averages (green and black lines) and the final shares of the nationwide two-party vote (green and black diamonds at 0 days). Clinton lost despite garnering 51.05 percent of the nationwide two-party vote. Biden won narrowly — because of razor-thin victories in several states — even though he got 52.25 percent of the two-party vote. Harris’s performance currently lags Clinton’s, which is a good sign for Trump.

The red line at 52.5 percent is my estimate of what it will take for Harris to register a clear victory over Trump. Harris is moving away from that number, not toward it.

Third, I adjust polling averages for anti-Trump bias. Of the polling organizations surveyed by RCP, 17 released polls in the final week before the 2020 election. Fourteen of the polls overestimated Biden’s popular-vote margin, with overestimates ranging from 0.5 to 7.5 percentage points. Only three pollsters underestimated Biden’s margin, with a range of 0.5 to 3.5 points. The overall average for the 17 pollsters was an overestimate (for Biden) of 3.7 points.

Because Trump is again the GOP nominee, I see no reason to assume that the pro-Democrat bias this year is any smaller than it was in 2020. So I simply add 3.7 points to Trump’s 7-day polling average to get a truer picture of Trump’s electoral appeal. I then compute a 95-percent confidence interval around the current 7-day average. As of today, the range spans a Trump lead of 1 percentage point to a Trump lead of 7 percentage points. I also compute a 95-percent confidence interval around the current 7-day average, unadjusted for bias. As of today, that spans a Trump deficit of 2 percentage points to a Trump lead of 5 percentage points.

How does that range translate into electoral votes? Here’s how, Trump would win 291 to 343 electoral votes if the election were held today:

(See “Trump vs. Biden: 16” for an explanation of the relationship between popular vote/polling margin and electoral votes.)

The fact that the low end of the range exceeds 270 electoral votes should give Trump supporters cause for optimism about the outcome of the election.

Turning to new material, I begin with a Gallup poll (conducted 415 times since January 2004) that probes adults’ party affiliations. When independents are allocated based on their leanings, the two-party split looks like this:

I plotted the average results for the month before each election (2004, 2008, 2012, 2016, and 2020) against the GOP candidates’ shares of the two-party vote in those elections. The result is spuriously precise, given the small number of observations, as is any projection based on it. But it supports the inference that the recent high level of GOP-leaning adults (54% thus far in October 2024) portends a popular-vote majority for Trump:

(Gallup’s party-affiliation numbers can be found here. Gallup has produced other analyses that also portend a shift toward the GOP).

Finally, I turn to Nate Silver’s Silver Bulletin. Much of his material is accessible only to subscribers, so I will omit the links in the following quotations. Today’s election forecast begins with this:

Last update: 1:45 p.m., Sunday, October 20. The data continues to be pretty negative for Kamala Harris. There are now three recent high-quality national polls that show Donald Trump leading — a difficult circumstance for Harris, given Democrats’ Electoral College disadvantage — and her edge in our national polling average is down to 1.7 points. National polls don’t influence the model that much, and the race remains basically a toss-up, but it’s not hard to think of reasons that Trump could win.

There’s a link in that passage which leads to 24 reasons why Trump could win:

This election remains extremely close, but Donald Trump has been gaining ground. One of my pet peeves is with the idea that this is Kamala Harris’s election to lose. I could articulate some critiques of her campaign, but if you study the factors that have historically determined elections, you’ll see that she’s battling difficult circumstances.

So, today’s newsletter simply aims to provide a laundry list of factors that favor Trump, with many links to evidence in previous Silver Bulletin posts and elsewhere. These are in no particular order.

Harris is the favorite to win the popular vote, but The Electoral College bias favors Republicans by about 2 percentage points. In an era of intense partisanship and close elections, this is inherently difficult for Democrats to overcome.
Inflation hit a peak of 9.1 percentage points in June 2022. It has abated now, but prices remain much higher than when Biden took office, and voters are historically highly sensitive to inflation. Democrats can also plausibly be blamed for it given intensive increases in government spending during COVID recovery efforts.
Though the reasons for this are much debated, voter perceptions about the economy lag substantially behind objective data, and growth in take-home income has been sluggish for many years for the working class amid rising corporate profits.
Incumbent parties worldwide are doing very poorly, and the historical incumbency advantage has diminished to the point where it may now be an incumbency handicap instead amid perpetually negative perceptions about the direction of the country.
Populism is often a highly effective strategy, and many Trump voters are indeed “deplorable” in the Hillary Clinton sense of the term.
Illegal/unauthorized immigration increased substantially during the first few years of the Biden/Harris administration amid a rising global backlash to immigration.
Harris ran far to her left in 2019, adopting many unpopular positions, and doesn’t really have a viable strategy for explaining her changing stances.
The cultural vibes are shifting to the right, and the left continues to pay a price for the excesses of 2020 on COVID, crime, “wokeness,” and other issues.
Voters have nostalgia for the relatively strong economic performance in the first three years of Trump’s term and associate the problems of 2020 with Democrats, even though they weren’t in charge at the time.
Democrats’ dominance among Black voters and other racial and ethnic minority groups is slipping. It may be unfortunate timing: the memory of the Civil Rights Era is fading. Educational polarization, which implies deteriorating Democratic performance among working-class voters of all races, may also be coming to dominate other factors. It’s possible this works out well for Democrats if Harris makes corresponding gains among white voters, who pack more leverage in the Electoral College, but there’s no guarantee.
Many men, especially young men, feel lost amidst declining college enrollment, contributing to a rightward shift and a growing gender gap.
Joe Biden sought to be president until he was 86. Voters had extremely reasonable objections to this, and it neuters what should have been one of Harris’s best issues about Trump’s age and cognitive fitness.
Harris also got a late start to her race, inheriting most of the staff from the poorly-run Biden campaign. She’s proven to be a good candidate in many respects, but it’s always a big leap when the understudy is suddenly thrust into the spotlight.
Harris is seeking to become the first woman president. In the only previous attempt, undecideds broke heavily against Hillary Clinton, and she underperformed her polls.
Trust in media continues to fall to abysmal levels. One can debate how to attribute blame for this between longstanding conservative efforts to discredit the media, a secular decline in trust in institutions, and various overreaching and hypocrisy in the press. But it’s hard for even legitimate Trump critiques to penetrate the mass public. Trump’s conviction on a series of felony charges hardly made any difference, for instance.
Trump has traits of a classic con man, but con artistry is often effective, and Trump is skilled at convincing voters that he’s on their side even if his election would not be in their best interest. Furthermore, Trump presents Democrats with a Three Stooges Syndrome problem: a range of plausible attacks so vast that they tend to cancel one another out.
Democrats’ college-educated consultant class has poor instincts for how to appeal to the mass public, while Trump has done more to cultivate support among “weird” marginal voting groups.
Democrats’ argument that Trump is a critical threat to democracy is valid and important, given January 6 and Trump’s broad disrespect for the rule of law. But it’s a tough sell: ultimately, January 6 was a near-miss — it could very, very easily have been much, much worse — and Democrats hold the White House, the Senate, and many key governorships now. It isn’t intuitive to voters that democracy is threatened and Democrats may have staked too many chips on this line of attack.
Foreign policy might not matter much to voters, but the world has become more unstable under Biden’s tenure. There has been a decline in democracy worldwide and an increase in interstate conflict, crises in the Middle East and Ukraine, deteriorating US-China relations, increasing immigration flows because of global instability, and a pullout from Afghanistan that negatively impacted Biden’s popularity.
The Israel-Hamas war split the Democratic base in a way no comparable issue has split the GOP base.
There are more left-leaning third-party candidates than right-leaning ones, and the former leading third-party candidate (RFK Jr.) endorsed Trump and undermined Harris’s post-convention momentum.
The richest man in the world, Elon Musk, has become a huge Trump stan and is doing everything in his power to tip the election to him. Twitter/X remains an influential platform among journalists but has shifted far to the right. Elon and Silicon Valley have also created a permission structure for other wealthy elites to advocate for Trump explicitly and provided a new base of money and cultural influence.
Trump was very nearly killed in an assassination attempt, and then there was a second one against him. The first attempt was closely correlated with an increase in favorability ratings for Trump, and polling shows he’s considerably more popular and sympathetic than in 2016 or 2020.
Harris has been running on vibes and has failed to articulate a clear vision for the country. It might have been a good strategy if the “fundamentals” favored her, but they don’t.

Trump vs. Harris: 3 (Some Favorable News for Trump)

I follow the presidential polling summaries published at Real Clear Politics (RCP). I analyze the polling results in various ways. Three of those ways are highlighted here.

First, I track each pollster’s poll-to-poll change in Trump’s lead or deficit. Assuming that each pollster’s bias for or against Trump (mostly against) remains about the same, the poll-to-poll changes indicate the direction of momentum. The “Harris Honeymoon” seems to have ended:

Second, I adjust polling averages for anti-Trump bias. Of the polling organizations surveyed by RCP, 17 released polls in the final week before the 2020 election. Fourteen of the polls overestimated Biden’s popular-vote margin, with overestimates ranging from 0.5 to 7.5 percentage points. Only three pollsters underestimated Biden’s margin, with a range of 0.5 to 3.5 points. The overall average for the 17 pollsters was an overestimate (for Biden) of 3.7 points.

Given that Trump is again the GOP nominee, I see no reason to assume that the pro-Democrat bias this year is any smaller than it was in 2020. So I simply add 3.7 points to Trump’s 7-day polling average to get a truer picture of Trump’s electoral appeal. I then compute a 95-percent confidence interval around the current 7-day average. As of now, the range is from a deficit of 1 percentage point to a lead of 6 percentage points.

How does that range translate into electoral votes? Here’s how, Trump would win 312 to 343 electoral votes if the election were held today:

(See “Trump vs. Biden: 16” for an explanation of the relationship between popular vote/polling margin and electoral votes.)

Third, I compare Harris’s performance in the polls (unadjusted) with the performances of Clinton in 2016 and Biden in 2020.

The red line at 52.5 percent is my estimate of what it will take for Harris to register a clear victory over Trump. Harris is still a long way from that number.

And ‘Mid This Tumult …

… Kubla heard ancestral voices prophesying war!

— Samuel Coleridge Taylor, Kubla Khan: or a Vision in A Dream

* * *

I write today with deep pessimism about America’s future. The immediate source of my dark mood is the massive missile attack on Israel. The attack means that Israel’s war against its Muslim enemies is entering a phase that could directly involve the United States. Whether that’s a good or bad thing for the U.S. will depend on Israel’s success (or failure); subsequent responses by Iran, China, Russia, and North Korea; and subsequent U.S. military action. But it is telling that Iran chose to attack Israel directly, for a second time, despite U.S. warnings and the buildup of combat-ready U.S. forces in the region of conflict.

The (perhaps terminally foolish) boldness of Iran’s leaders reinforces my pessimism about the current U.S. administration’s willingness to take advantage of an opportunity to de-fang Iran and to let the other members of the axis of evil know that it’s time to stop messing around with Uncle Sam. By de-fang, I don’t mean a one-shot, tit-for-tat response to Iran’s missile attack on Israel. I mean a series of decisive military actions — undertaken in alliance with Israel — that remove Iran’s ability to wage war beyond its borders, including the ability to make and deliver nuclear weapons.

The problem of unwillingness reflects, in part, the problem of inability, which is owed in the first pace to the problem of unwillingness. I refer you to my “Grand Strategy for the United States“, which is a few years out of date. For a current view of the state of U.S. military power, see Walter Russell Mead’s “U.S. Shrugs as Word War III Approaches” (The Wall Street Journal on September 16, 2024, paywalled). This is from Mead’s piece:

The news from abroad is chilling. Washington Post columnist David Ignatius reports from Kyiv that Ukraine is “bleeding out” as its weary soldiers struggle against a numerically superior Russia. The New York Times reports that China is expanding the geographical reach and escalating violence in its campaign to drive Philippine forces from islands and shoals that Beijing illegitimately claims. And Bloomberg reports that Washington officials are fearful that Russia will help Iran cross the finish line in its race for nuclear weapons.

These stories, all from liberal news outlets generally favorable to the Biden administration, tell a tragic and terrifying tale of global failure on the part of the U.S. and its allies. China, Russia and Iran are stepping up their attacks on what remains of the Pax Americana and continue to make gains at the expense of Washington and its allies around the world.

What none of these stories do is connect the dots by analyzing the consequences of repeated American failure on the widely separated fronts of the international contest now taking place. To see what this all means and where it is leading, we must turn to the recently released report of the Commission on the National Defense Strategy. This panel of eight experts, named by the senior Republicans and Democrats on the House and Senate Armed Services committees, consulted widely across government, reviewing both public and classified information, and issued a unanimous report that, in a healthy political climate, would be the central topic in national conversation.

The bipartisan report details a devastating picture of political failure, strategic inadequacy and growing American weakness in a time of rapidly increasing danger. The U.S. faces the “most serious and most challenging” threats since 1945, including the real risk of “near-term major war.” The report warns: “The nation was last prepared for such a fight during the Cold War, which ended 35 years ago. It is not prepared today.”. . .

Should such a conflict break out, “the Commission finds that the U.S. military lacks both the capabilities and the capacity required to be confident it can deter and prevail in combat.”

To summarize, World War III is becoming more likely in the near term, and the U.S. is too weak either to prevent it or, should war come, to be confident of victory.

A more devastating indictment of a failed generation of national leadership could scarcely be penned.

(You should also read David Masci’s “The Wages of Fecklessness” at Discourse [September 29, 2024], and “America’s Enemies Race for Nuclear Dominance” by James E. Farrell and Bradley A. Thayer at American Greatness [September 29, 2024].)

If there is a decisive Israeli-American action against Iran, it will become evident to all (excepting the Biden administration and its leftist allies in America) that the U.S. was the junior partner in the undertaking.

That’s ominous enough. What’s perhaps more ominous than the prospect of America’s descent into the ranks of military also-rans is its almost-certain inability to prevent a series of devastating terrorist attacks on U.S. soil. Such attacks will precede or coincide with a military demonstration by China, Russia, and North Korea (if not Iran). The military demonstration would include cyber-attacks on critical U.S. military and infrastructure targets. (See this and this about the threat of cyber-war.)

The aims of the terrorist attacks and military demonstration will be these, at least:

Demoralization of the U.S. and its traditional allies in Canada, the British Isles, Western Europe, East Asia, Australia, and New Zealand.
Acquiescence by the U.S. and its traditional allies in the territorial and economic objectives of the axis.

The terroristic aspect of this strategy will be executed by the army of terrorists which has been able to infiltrate the U.S. in the past several years due to the Biden administration’s effort to recruit illegal immigrants (future voters) to its quest for a permanent Democrat majority:

Tens of thousands of illegal immigrants with sex offenses and homicide convictions could be loose on the streets, according to Immigration and Customs Enforcement (ICE) data provided to lawmakers this week.

The agency provided data to Rep. Tony Gonzales, R-Texas, about national data for illegal immigrants with criminal charges or convictions. The data, as of July 2024, is broken down by those in detention, and those who are not in detention — known as the non-detained docket. The non-detained docket includes illegal immigrants who have final orders of removal or are going through removal proceedings but are not detained in ICE custody. There are currently more than 7 million people on that docket.

The data say that, among those not in detention, there are 425,431 convicted criminals and 222,141 with pending criminal charges.

Those include 62,231 convicted of assault, 14,301 convicted of burglary, 56,533 with drug convictions and 13,099 convicted of homicide. An additional 2,521 have kidnapping convictions and 15,811 have sexual assault convictions.

There are an additional 1,845 with pending homicide charges, 42,915 with assault charges, 3,266 with burglary charges and 4,250 with assault charges. [Adam Shaw, “Tens of Thousands of illegal Immigrants with Sexual Assault, Murder Convictions in US: ICE Data“, Fox News, September 28, 2024]

What about terrorists? There have been reports of persons on terrorist watch-lists having been apprehended at the southern border. Obviously, there have been no reports of terrorists (known or unknown) who have eluded detection and are now setting their plans in motion. But given the magnitude of the incursion of criminals, it’s not inconceivable that there are tens of thousands of terrorists in cells dotted around the country, waiting for orders to proceed with a series of attacks.

What might these minions of the axis do? There are so many possibilities that I can’t begin to list them. I’ll restrict myself to a scenario that I depicted in 2011:

A large but dispersed collection of improvised weapons for improvised, mortar-style attacks has been gathered in and around major U.S. cities and transportation and energy nodes.

These weapons are positioned so that their activation, on a massive scale would create havoc and panic — and might well disrupt transportation and communication networks. (With a massive salvo, not every weapon must reach its target.)

These weapons can be activated remotely — perhaps through signals transmitted from a single point — so that they can be fired in coordinated waves. Each successive wave disrupts and complicates rescue and recovery efforts that ensue from preceding waves, heightens confusion and panic, and lays the groundwork for economic disaster and political repression.

I added this in 2015:

A 2013 attack on an electric substation near San Jose that nearly knocked out Silicon Valley’s power supply was initially downplayed as vandalism by Pacific Gas & Electric Co., the facility’s owner. Gunfire from semiautomatic weapons did extensive damage to 17 transformers that sent grid operators scrambling to avoid a blackout.

But this week, a former top power regulator offered a far more ominous interpretation: The attack was terrorism, he said, and if circumstances had been just a little different, it could have been disastrous.

Jon Wellinghoff, who was chairman of the Federal Energy Regulatory Commission when the shooting took place, said that attack was clearly executed by well-trained individuals seeking to do significant damage to the area, and he fears it was a test run for an even larger assault.

“It would not be that hard to bring down the entire region west of the Rockies if you, in fact, had a coordinated attack like this against a number of substations,” Wellinghoff said Thursday. “This [shooting] event shows there are people out there capable of such an attack.”

Wellinghoff’s warning about the incident at PG&E’s Metcalf substation was reported this week by the Wall Street Journal, expanding on a December report by Foreign Policy magazine.

FBI officials said they are taking the shooting very seriously.

“Based on the information we have right now, we don’t believe it’s related to terrorism,” said Peter Lee, an FBI spokesman in San Francisco. But, he added, “Until we understand the motives, we won’t be 100% sure it’s not terrorism.”

Months after the shooting, the bureau has named no suspects.

Potential terrorism scenarios usually involve elaborate cyberattacks, expertly executed hijackings or smuggled nuclear weapons. But concern grows that California may have come unnervingly close to learning that calamity might just as easily be inflicted by a few well-trained snipers.

As law enforcement tries to piece together who fired at the electricity facility, lawmakers and analysts express bewilderment that little is being done to protect against a repeat performance….

The classified report was completed in 2007 and became public two years ago. Asked what has happened since then to protect the nation’s electricity system, Morgan replied that very little has been done.

The attack on the PG&E facility targeted the sophisticated transformers that are at the backbone of the nation’s electricity grid. The giant pieces of equipment are essential, costly and could take months to replace. Knock out enough of them, experts warn, and an entire region can be crippled for an extended period. They are also typically out in the open like sitting ducks.

On that April night, the attackers managed to disable 17 of them just by shooting through a chain-link fence. The bullet holes caused the transformers to leak thousands of gallons of oil, and ultimately overheat. Grid operators scrambled to reroute power from elsewhere to keep the system from collapse. The power stayed on, but just barely, because it happened during a time when demand for electricity was very low.

“Fortunately it was spring and we did not have air conditioners running full throttle in the morning,” said Stephanie McCorkle, a spokeswoman for the California Independent System Operator in Folsom, which runs most of the state’s electrical grid. “That’s why the situation was manageable.”

Wellinghoff, now a partner at the San Francisco law office Stoel Rives, said the grid’s interdependence on substations across large swaths of the country — and a scarcity of spare equipment — makes it possible to trigger an enduring blackout across several states simply by destroying key transformers in one of them.

Days after the April shooting, Wellinghoff flew out to review the damage with experts from the Pentagon and the FBI. They noticed piles of stones had been set up outside the site, apparently by someone who had scoped it out to guide the snipers. [Evan Halper and Mark Lifsher, “Attack on Electric Grid Raises Alarm,” Los Angeles Times, February 6, 2015]

It may be too late for a contemporary Churchill to reignite America’s long-lapsed fighting spirit. Moreover, if a contemporary Churchill were to ascend to power in the U.S., he would be reviled and opposed by the leftist quislings who have come to the fore in this country.

If the past is prologue, America’s wartime “exploits” since World War II foreordain its ignominious end.

Perhaps my dark mood will lift. I hope that the events of the next few days and weeks will cause it to do so.

Share this:

Share this:

Share this:

Share this: