December 12, 2023

#AI ChatGPT - OpenAI: A question on behalf of FT and Martin Wolf.

 In "Britain needs a growth strategy" Martin Wolf mentions the UK has for too long settled for managing stagnation.

On behalf of FT and Martin Wolf I decided to ask ChatGPT:

"Could bank capital requirements that favors “safe” government debt and residential mortgages over “risky” loans to small businesses and entrepreneurs, doom a nation to stagnation?"

ChatGPT answered:

"The impact of bank capital requirements on economic growth is a complex and debated topic among economists. Capital requirements are regulations set by financial authorities that determine the amount of capital a bank must hold in relation to its assets. These requirements are designed to ensure the stability of the financial system by reducing the risk of bank failures.

If capital requirements heavily favor "safe" assets such as government debt and residential mortgages over "risky" loans to small businesses and entrepreneurs, it can potentially have both positive and negative effects on the economy.

Potential Positive Effects:

Financial Stability: By incentivizing banks to invest in safer assets, capital requirements can contribute to financial stability. This reduces the likelihood of bank failures, which could have broader systemic consequences.

Investor Confidence: Investors and depositors may feel more secure knowing that banks are holding assets that are considered safer, leading to increased confidence in the financial system.

Potential Negative Effects:

Stifling Innovation and Growth: If banks are discouraged from lending to small businesses and entrepreneurs, it could hinder innovation and economic growth. Small and medium-sized enterprises (SMEs) are often drivers of job creation and economic dynamism.

Inequality: Focusing on "safe" assets may exacerbate economic inequality. Small businesses, startups, and entrepreneurs, which are crucial for innovation and job creation, might face difficulty accessing the necessary funding.

Reduced Economic Diversity: A banking system overly concentrated on certain types of assets may lead to reduced economic diversity. This can make the economy more vulnerable to shocks in specific sectors.

Long-Term Stagnation: Overemphasis on "safe" assets might lead to a lack of risk-taking and investment in new ventures, potentially resulting in long-term economic stagnation.

Balancing Act:

It's crucial for financial regulators to strike a balance between stability and promoting economic growth. Prudent capital requirements that consider the riskiness of assets, while still allowing banks to support economic development, can be important. Striking the right balance often involves ongoing adjustments to regulations based on economic conditions and lessons learned from past experiences.

In conclusion, while capital requirements that favor "safe" assets can contribute to financial stability, an excessive focus on them at the expense of riskier but potentially innovative investments could indeed have negative consequences for a nation's economic dynamism and growth. The challenge lies in finding a regulatory framework that mitigates risk without stifling entrepreneurial activity and economic progress."

Thanks!

ChatGPT answered: You're welcome! If you have any more questions or if there's anything else I can help you with, feel free to ask. Happy to assist!

Note: The answers are copied exactly from those given to me by OpenAI


Comment: Way back, 2009, Martin Wolf was kind to publish in his Economic Forum an articled I titled "Please free us from imprudent risk aversion and give us some prudent risk-taking." I stand by it more than ever.

November 11, 2023

An adequate response to a Covid pandemic needs more views than what epidemiologists and statisticians can provide.

Sir, I refer to “Please put statisticians in charge of data for the next crisis” Sir David Norgrove, FT November 11.


July 2020, I tweeted:

Sweden kept all schools until 9th grade open. Parents of children in 9th grade are almost always less than 50 years of age. In Sweden, as of July 24, out of 5,687 Coronavirus deaths 71, 1.2%, were younger than 50 years.

Conclusion: Keep schools open, keep older teachers at home and have grandparents refrain from hugging their grandchildren. Disseminating data on COVID-19 without discriminating by age, is in essence misinformation.



October 2020 the Washington Post published a letter in which I opined:

“Roughly 90% of all coronavirus deaths will occur in those 60 years of age and older. 
Equally roughly 90% of the virus’s social and economic consequences will be paid by those younger than 60. It’s an intergenerational conflict of monstrous proportions."


March 2021 I tweeted:

“Georges Clemenceau’s “War is too serious a matter to entrust to military men” could be updated to: A Covid-19 response ‘is too serious a matter to entrust’ to epidemiologist”

At this moment I feel that besides not entrusting epidemiologists I might have to include some statisticians e.g., from the UK Statistic Authority. They must have known it, so why did they not speak up?


June 2023 I asked ChatGPT-OpenAI:

"Suppose a virus hits a nation, and to its authorities it's evident that its mortality rate depends the most on age. In such a case, transmitting data to the population about the total number of deaths without discriminating this by age, could that be deemed to be misinformation?"

A.I. answered:
"In the scenario you described, if the authorities have clear evidence that the mortality rate of the virus is significantly influenced by age, transmitting data about the total number of deaths without providing any information or context about age distribution could be considered incomplete or potentially misleading information”


Sir David Norgrove ends his opinion with “Churchill recognized the need for high quality statistics to help him run the war.”

In March 2020 I tweeted:

“In February, I visited Churchill War Rooms in London Reading UK’s plans of building up herd immunity against coronavirus, I have a feeling Winston would have agreed with such stiff upper lip policy: “I have nothing to offer but fever, coughing, chills and shortness of breath”

Now I ask you Sir. Is this not a kind of document that should be presented to any Covid type of inquiry that, without fear and without favour, really dares to get to the bottom of the problems? 

@PerKurowski

July 17, 2023

How long will it take for bank regulators to ask AI regulators for a little favour?

Sir, Michael Skapinker writes: “Why did no one speak up “inside Sil­icon Val­ley Bank before it col­lapsed? People thought speak­ing up would leave them vulnerable to vic­tim­isa­tion.” “Listen and you might learn something” FT July 17.

Thought, or knew? 

What should a risk manager know about the risk of informing the board that according to revised models that included the interest rate risk (duration), SVB’ risk weighted capital/equity requirements would increase substantially? 

Would a bank supervisor like to go on record informing his superiors, the regulators, that because of IRR, the 0% risk weighting of long-term US Treasury bonds made no sense?

Sir, instead of exposing humans to victimisation, it seems precisely the moment that we could make great use of artificial intelligence. 

E.g., I asked ChatGPT – OpenAI: “Should regulators and supervisors be aware of risks with US Treasury long-term bonds? 
It answered: “Yes, they should be aware of the duration risk and interest rate risk associated with long-term Treasury bonds held by banks”

But of course, AI could be vulnerable to victimisation too.

I asked Open AI:” Can those who become an Artificial Intelligence regulator, make you or any other AI participants agree with all they want you to agree with?” 
It answered: “Regulators aim to address ethical considerations, potential risks, and ensure responsible AI practices… AI systems don't possess independent consciousness or the ability to willingly agree or disagree with regulations. Their behavior is determined by their programming and the data they have been trained on.”

Sir, you know much to well, that for more than two decades I’ve been vociferating, as much as I can, my criticism against the risk weighted bank capital requirements. Clearly when someone does want to hear, he does not hear. For instance, as Upton Sinclair Jr. explained it: “It is difficult to get a man to understand something, when his salary depends on his not understanding it.”

Therefore, when I heard about OpenAI, I asked it a series of questions. From the answers you must agree I found an ally. I just wonder how long it will take for bank regulators to shut it up. “We can’t have someone questioning the risk weights of 0% government – 100% citizens. Can we?”

How long will it take to FT to really listen to some of its faithful subscribers?

PS. US Treasury long-term bonds still carry a 0% risk weight.

June 25, 2023

A strong national spirit/character is what’s most needed for any preparedness, even against a pandemic.

Sir, I refer to Tim Harford’s “Is it even pos­sible for coun­tries to pre­pare for a pan­demic?” FT June 24, 2023.

“Be pre­pared! It’s the scout’s motto. But pre­pared for what?” I was never a boy-scout but as I have understood that movement it was to be prepared courageously for the unexpected, not silently accepting a lockdown; and to be able to lit a fire without matches, not to learn to deploy sewage monitors.

So sadly, though Harford does indeed know much of economy, here I think he does not even scratch the surface of what’s most needed, like:

First: The understanding that, for a nation/society as a whole, a response to the pandemic can be much more harmful than the pandemic itself.

Second: That just as George Clemenceau opined, “War is too serious a matter to entrust to military men”, a pandemic is also too serious a matter to entrust to epidemiologists” Any preparedness against a pandemic must include a wide diversity of opinions.

Third: Information, information and information: With respect to this Harford mentions: “Joshua Gans, eco­nom­ist and author of The Pan­demic Inform­a­tion Solu­tion (2021), argues that we’ve learnt that pan­dem­ics can be thought of as inform­a­tion and incentive problems.” No, begin by giving the people full information and then let them understand and decide if and what incentives are needed.

In July 2020 I tweeted:
“Sweden kept all schools until 9thgrade open. Parents of children in 9th grade are almost always less than 50 years of age. In Sweden, as of July 24, out of 5,687 Coronavirus deaths 71, 1.2%, were younger than 50 years.”
“Conclusion: Keep schools open, keep older teachers at home and have grandparents refrain from hugging their grandchildren. Disseminating data on Covid-19 without discriminating by age, is in essence misinformation.”

Clearly information on the relation between Covid-19 and age was available but was not sufficiently provided. One explanation could be that the Covid-19 pandemic hit the world in the midst of a polarization pandemic. 17 October 2020 I wrote in a letter to FT “way too many polarization profiteers just don’t want harmony vaccines to appear.”

March 2020 I tweeted: 
“In February, I visited Churchill War Rooms in London Reading UK’s plans of building up herd immunity against coronavirus, I have a feeling Winston would have agreed with such stiff upper lip policy: “I have nothing to offer but fever, coughing, chills and shortness of breath”

Sir, Neville Chamberlain’s spirit inspired UK’s pandemic answer. Just like he is present in the risk weighted bank capital requirements which incentivize much more the refinancing of the “safer” present than the financing of the “riskier future”

I summarized the result of the above three failings in a letter published by the Washington Post in October 2020 in which I stated: "Roughly 90% of all coronavirus deaths will occur in those 60 years of age and older. Equally roughly 90% of the virus’s social and economic consequences will be paid by those younger than 60. It’s an intergenerational conflict of monstrous proportions."

PS. Sir, if you are interested you might want to read what ChatGPT – OpenAI answered when I asked "Suppose a virus hits a nation, and to its authorities its evident that its mortality rate depends the most on age. In such a case, transmitting data to the population about the total number of deaths without discriminating this by age, could that be deemed to be misinformation?"

PS. Sir, you should be interested in the above, it evidences how humans can begin dialoguing with artificial intelligence, so as to have a better chance of keeping their Human Masters and appointed experts in check.

@PerKurowski

April 17, 2023

To stand a chance, UK must refrain from imprudent risk-aversion and embrace some prudent risk-taking.

Sir, I refer to Martin Wolf’s “The UK’s future depends on improving economic performance” FT, April 15 2023. 

Wolf at the end of it recommended the UK to “reform its pension system, in order to generate more risk-taking capital, create dynamic new businesses.” Why does Wolf not even mention the UK's banks?

From mid 1979 until mid 1980 I practiced at Kleinwort Benson, one of the truly old English Merchant Banks that has since then, as so many others, gone down, disappeared by globalized Basel Committee bank regulations. With the risk weighted bank capital (equity) requirements, knowledgeable and experienced loan officers were substituted by creative equity-minimizing / leverage-maximizing (dangerously creative) financial engineers.

October 2009, in his Economist Forum, Martin Wolf published my: “Please free us from imprudent risk-aversion and give us some prudent risk taking” It began it with “There is not one single reason to believe the world would be a better place because our financial regulators provide additional incentives to those who, perceived as having a lower risk of default, are already favored by lower interest rates, or punish further those who, perceived as more-risky, are already punished by higher interest rates. In fact, the opposite is most likely truer”

Sir, when comparing government debt and residential mortgages with loans to small businesses and entrepreneurs, in terms of how nutritive they could be for the economy, it is not that outlandish to describe it as demand-carbs vs supply-proteins.

In “Credit Suisse: the rise and fall of the bank that built modern Switzerland” FT, March 24, Owen Walker and Stephen Morris write the Schweizerische Kreditanstalt, later rebranded as Credit Suisse, was born out of Alfred Escher’s determination to develop a railway network across the Alpine nation that would link northern and southern Europe. 

Sir, would that Alpine railroad have been built, with a Basel Committee imposing risk weighted bank capital/equity requirements with decreed weights 0% government, 30% residential mortgages and 100% risky projects? 

Would the banks in the City of London have reached the stars with such regulations?

Sir, dare ask Martin Wolf to dare answer that.

@PerKurowski

April 03, 2023

Are British authorities more aware of risks than those in the US? Martin Wolf, dare find out.

Sir, Martin Wolf writes “The best pro­tec­tion against occa­sional huge bank­ing crises is fre­quent smal­ler ones.” “The UK must learn its own les­sons from the bank­ing crisis” FT April 3, 2023.

“There is a thesis that holds that the old agricultural traditions of burning a little each year, thereby getting rid of some of the combustible materials, was much wiser than today’s no burning at all, that only allows for the buildup of more incendiary materials, thereby guaranteeing disaster and scorched earth, when fire finally breaks out, as it does, sooner or later. 
Therefore, a regulation that regulates less, but is more active and trigger-happy, and treats a bank failure as something normal, as it should be, could be a much more effective regulation. The avoidance of a crisis, by any means, might strangely lead us to the one and only bank, therefore setting us up for the mother of all moral hazards—just to proceed later to the mother of all bank crises.”
Also, knowing that ‘the larger they are, the harder they fall,” if I were regulator, I would be thinking about a progressive tax on size”

But Wolf begins with “Banks are the Achilles heel of the mar­ket eco­nomy. The com­bin­a­tion of risky long-term assets with liquid liab­il­it­ies redeem­able at par is a stand­ing invit­a­tion to illi­quid­ity and insolv­ency.” On that I would like to point out that in the case of SVB, those “risky long-term assets” were US Treasury bonds, assigned a 0% risk weight by the regulators. Current risk weighted bank capital/equity requirements are the real Achilles heel of the mar­ket eco­nomy. Had these not existed, and there instead had been one single capital requirement against all assets e.g., 10%, there’s no chance SVB (or other banks) would have so much ignored the interest rate risk, the duration risk, present.

Just think of what must be a modern bank risk manager’s risk dilemma: “What if my risk model shows the risks of the bank’s assets have increased a lot and therefore the bank’s capital/equity requirements will have to increase a lot too? What will the Board say?”

Wolf writes: “As Charles Good­hart of the Lon­don School of Eco­nom­ics has noted, man­agers who fail to man­age suc­cess­fully must share — and know they will share — in the losses”. I ask, should that not apply to regulators too? Should those who with so much hubris have/are betting our bank systems on that they know so much about risks, not at least be paraded down some major avenues wearing cones of shame?

Finally, Wolf hopes that “The Brit­ish author­it­ies appear to have been much more aware of the risks cre­ated by losses on the mar­ket value of port­fo­lios caused by higher interest rates than those in the US.” Why does he not investigate if its so? Is he scared he, like most, will have been duped/lulled into a false sense of security believing that risk weighted assets (RWA) is a sufficiently good reflection of bank risks?

January 23, 2023

For our grandchildren sake we must recover the “democratic capitalism” we inherited and lost too much of.

“We have inherited democratic capitalism from the struggles of our predecessors. We must reform and protect it for our descendants.” Martin Wolf, “In defence of democratic capitalism” FT January 21, 2023

Yes, indeed, but Sir, sadly, we’ve already lost too much of it. When I see bank capital requirements with decreed risk weights of 0% government and 100% citizens, I see Hitler/Stalin/Mao/Mussolini decreed weights… I see populism… I see the empowerment of an authoritarian bureaucracy autocracy… I see the dangerous and weakening distortion of the allocation of bank credit.

And that’s why, even to the point of obsession (as Wolf once mentioned) I’ve been fighting the risk weighted bank capital (equity / shareholders’-skin-in-the-game) requirements, first introduced 1988, as Basel I. These allow banks to leverage more their shareholders’-skin-in-the-game, and thereby earn higher risk adjusted returns on equity when financing what’s perceived (or decreed) as safe, than when financing what’s perceived as risky.

That de facto decreed the more creditworthy as more worthy of credit and the less creditworthy as less worthy of credit.

Wolf opines “It is possible for example to limit macroeconomic instability by reducing reliance on debt-fuelled demand and making the financial system more robust”. Yes, but for that Wolf must try to understand that what’s “safe” e.g., government debts and residential mortgages are more like demand-pushing-carbs while, what’s “risky” e.g., loans to small businesses and entrepreneurs, could be classified as supply-producing-proteins.

These regulations were sold as making our bank systems safer. What nonsense. The large exposures that have caused all major bank crises have always been built up with assets perceived (or now decreed) as safe, and never ever with assets perceived as risky.

The real reason for it all was confessed by Paul Volcker in his 1988 autobiography “Keeping at it”: “Assets for which bank capital requirements were nonexistent, were what had the most political support; sovereign credits and home mortgages… A ‘leverage ratio’ discouraged holdings of low-return government securities.”

Were those regulations agreed upon in a democratic way? Absolutely not. For a starter these should not be able to clear the American Founding Fathers’ US Constitution. 

Wolf mentions his family’s history: “In May 1940, as the Nazis invaded the Netherlands, my mother escaped from the country in a trawler hijacked by her father, a self-made fish merchant. Her father, one of nine, asked all his wider family to join them on the journey to England. None did: they were all slaughtered in the Holocaust.”

The morning after, everything’s clear but, the night before, who was the real risk-taker, Martin Wolf’s grandfather or the other eight who stayed behind?

In the same way the morning after a bank crisis, what’s dangerous becomes crystal clear. But what’s usually forgotten by Monday morning quarterbacks, is that the large exposures that caused the crisis were built up with assets perceived (or now decreed) as very safe. 

January 11, 2023

Creditworthiness should be grounded on what’s worthy of credit.

Sir, Martin Wolf writes “The vicious circle in which low creditworthiness begets unaffordable spreads, which beget debt crises and even lower creditworthiness.” “The threat of a lost decade in development”, Jan 11, 2023

NO! That vicious circle begins with too high decreed government creditworthiness. 

November 2004, the Financial Times published a letter in which I asked “How many Basel propositions will it take before they start realizing the damage they are doing by favoring so much bank lending to the public sector?”

Sincerely, anyone lending money to a developing country that has adopted Basel Committees’ bank regulations, based on that its bureaucrats know better what to do with that credit they’re not personally responsible for than e.g., its small businesses and entrepreneurs, deserves losing money.

When participating in the Sustainable Debt Levels (SDL) debate my opinion was always: “There cannot be a road more conducive to debt turning unsustainable, than to award credits just because they are sustainable.”

And what is development much about? The willingness to take risks. Where does Mr. Wolf thinks the western world would be with the current risk weighted bank capital requirements? In Nirvana or still among the emerging developing nations?

Friedrich List wrote that free trade was the means through which an already industrialized country “kicks away the ladder by which it has climbed up, in order to deprive others of the means of climbing up after it.” If we were to paraphrase List, if the high-income countries want to help, don’t kick away that ladder of risk taking that made them high-income.

1987, in reference to that credit risk aversion coming out of the Basel Committee for Banking Supervision, I ended my first Op-Ed ever with:

“If we insist on maintaining a firm defeatist attitude which definitely does not represent a vision of growth for the future, we will most likely end up with the most reserved and solid banking sector in the world, adequately dressed in very conservative business suits, presiding over the funeral of the economy. I would much prefer their putting on some blue jeans and trying to get the economy moving.”

Sir, I feel that paragraph being just as valid as then… and much worse, not only to developing nations.

PS. At the High-level Dialogue on Financing for Developing at the United Nations, New York, October 2007, this is the document I presented:

Subscribe to: Posts (Atom)