Germany's Murder Of Europe

  It looks more like a suicide to me! But this is what you get when a majority of uneducated imbeciles elect clowns to represent them. Whatever Europe does, it will not affect the climate nor other countries. Like the boycott of Russia, the green agenda will have exactly the opposite effect of what was expected. Better, the failure of the policies will be because Europe didn't do enough and they will double down on the hysteria. Is this how civilizations decline and finally crash?

Authored by Drieu Godefrei via The Gatestone Institute,

In a preparatory impact report, a copy of which has been obtained by the Financial Times before official release, the European Commission estimates that to achieve the target of reducing greenhouse gas emissions by 90% by 2040 then 100% in 2050 — the main objective of the "European Green Deal" — Europe will need to invest €1.5 trillion a year from 2031 to 2050.

1.5 trillion euros a year. That is equivalent to 10% of the Europe Union's entire GDP for 2022 -- every year! Apart from a war effort, there is no objective of any kind that has ever required the diversion of 10% of a continent's GDP by political decree.

The new German utopia

This number shows us that, while Germany has had to give up imposing its hatred of nuclear power on its European partners, it is determined to inflict on Europe the rest of the environmental utopia, i.e. total decarbonization, even at the cost of economic collapse and freedoms.

You may say that the European Commission is not Germany, but anyone who has worked in the Commission will tell you that there are two insurmountable lobbies at this level: Germany, by far is the most powerful country in Europe, followed by the environmental NGOs, such as Greenpeace and Friends of the Earth, which have permanent offices in the Berlaymont, the headquarters building of the European Commission. The fact that the current president of the Commission, Ursula von der Leyen, is German is just the icing on the apfelstrudel.

All the same, everything in this delirious report by the German Commission is wrong.

The Commission's pseudo-savvy calculations

The report states that the cost of inaction would be much higher than €1.5 trillion a year. In fact, explains the report, the European plan will save up to 1% of GDP per year. It should be noted, however, that this figure runs counter to all the IPCC's projections on the cost of global warming — which is 0.03 % of GDP per year, not 1%.

Annex 8 of the impact report just published by the Commission states:

"The IPCC AR6 Working Group II report (2022) confirms that global aggregate economic impacts generally increase with higher degree of global warming. However, due to the wide range of damage estimates and lack of comparability between methodologies, the report does not provide a robust range of estimates but recognizes that global aggregate economic impacts could be higher than estimated in the previous report."

In short, the IPCC's sixth report states that the cost of global warming could actually be greater than that stated in the fifth report.

Unfortunately (for lack of time? space? ink?) the Commission does not bother to reiterate what was said in the fifth report, which was voluble and precise on the question of the cost of global warming. Let us make up for this shortcoming: according to the fifth IPCC report AR5, chapter 10:

"For most economic sectors, the impact of climate change will be small relative to the impacts of other drivers... Changes in population, age, income, technology, relative prices... and many other aspects of socioeconomic development will have an impact on the supply and demand of economic goods and services that is large relative to the impact of climate change."

Above all, the Paris Agreement, of which the Commission claims to be part, aimed to limit global warming to only 1.5 degrees Celsius by 2100. Achieving this objective presupposed a drastic global reduction in human greenhouse global gas emissions, not just Europe. However, since 2015, these global emissions have continued to rise, and there is no realistic scenario in which global emissions will decrease. China, which still builds roughly two new coal-power plants a week, and India continue to lay waste to these projections.

Climate, of course, is a global issue: if Europe reduces its emissions to zero, while the rest of the world continues to increase them, the effect on the climate will be zero. As a result, the German plan will not save a single euro in terms of the damage caused by global warming and extreme events.

So, the investment needed each year would not be €1.5 trillion invested to save 0.03% of GDP per year. It would be €30 trillion — €1.5 trillion per year for 20 years — invested to change absolutely nothing in the climate of Europe.

There are no serious analysts left who still maintain that the objective of the Paris Agreement will be achieved; the Paris Agreement is obsolete and to pretend otherwise, as the European Commission is doing, is misleading, irresponsible, and not even scientific.

In addition, the report goes on to say that reducing European imports of fossil fuels would result in savings of up to €2.8 trillion between 2031 and 2050. At present there is no technical or scientific way of overcoming the intermittent nature of renewable energies such as wind, solar. As a result, Europe's energy mix will have to continue to rely on fossil fuels in addition to nuclear power, as demonstrated by Germany, the champion of lignite coal and CO2 emissions – and releasing ten times more CO2 than France, per unit of energy produced -- in 2024. What is more, this pseudo-savvy calculation presupposes that we know the prices of oil and gas in advance, and that we persist in banning the exploitation of the shale gas that lies beneath Europe's soil.

The report by the European Commission shows a frightening headlong rush. The situation in Europe is already dramatic. Since 2008, American GDP has doubled, meaning that Americans earn twice as much as they did in 2008. Since 2008, Europe's GDP has stagnated. This means that Europeans are increasingly taxed and harassed, and forbidden to move, build, undertake, innovate and start a family as they see fit, while their incomes are not increasing.

The shale revolution means that America now could be the world's largest producer of oil and gas, if President Joe Biden had not hobbled domestic energy production on his first day in office. The beneficiaries of his move were Russia, Iran -- and China, which can now more easily sell its cheap coal, thereby polluting the climate even more.

"Meanwhile," according to Gideon Rachman, chief foreign affairs commentator of the Financial Times, "energy prices in Europe have soared."

"The Ukraine war and the loss of cheap Russian gas mean that European industry typically pays three or four times as much for energy as their American competitors. Gloomy European bosses say this is already leading to factory closures in Europe".

In practical terms, whole swathes of our populations have entered into a pattern that is the ultimate dream of environmentalists: degrowth. In other words, their impoverishment. Giorgos Kallis, a prominent figure in the field of environmental economics, asserted recently the necessity of adopting a "degrowth" paradigm over the conventional GDP-based model. He contends that economies can and must thrive while simultaneously diminishing inequality and enhancing overall well-being.

Scenarios

Three possible scenarios emerge.

• In the first scenario, the EU will persist in its German ecological utopia, which will throw the whole of Europe even more deeply into the recession in which Germany is already languishing. In the context of its current economic stagnation, Europe cannot afford to divert 10% of its GDP per year to unaffordable, unreliable and intermittent energy sources. Popular revolts will multiply, making the current farmers' revolt look like "Pat the Bunny." It should be obvious that our democracies will not be able to withstand the impoverishment deliberately organized by "elites" who have gone mad trying to promote an insufficiently substantiated green ideology.

• In the second scenario, the EU would not undo the "European Green Deal," but its entry into force would simply be rescheduled (meaning postponed). This scenario condemns Europe to what economists Lawrence Summers and Henri Lepage name "secular stagnation," a condition when there is negligible or no economic growth in a market-based economy, on the model of Japan.

• A third scenario would see a new majority come to power through the European elections in June -- after all, what is the point of democratic elections if not to allow a change of course? -- and deconstruct (repeal) every piece of legislation in a European Green Deal that has become irrelevant or economically harmful to the most destitute among us in the current global context.

Ironically, if the IPCC's projections are to be believed, global warming may occur, and we will adapt to it through innovation. All the resources that Europe is burning up in a phantasmatic "energy transition", which has failed and will fail -- will just burn through money that we will then not have for innovation. What will Europe do when these misguided ideologies have permanently broken the back of its economy?

CBO Director Warns Of Debt Market Meltdown With US Debt Is On "Unprecedented" Trajectory

  In the new normal nothing ever happens. The Central Banks have our back so why worry? "Spending a life worrying for something that may or may not happen is no way of spending a life!" Fine. But as Hemingway said when he went bankrupt: Little by little then suddenly. For the US too, the sun will Set. It will be suddenly and it may not be in a faraway future.

CBO Director Warns Of Debt Market Meltdown With US Debt Is On "Unprecedented" Trajectory

We've been pointing it out for so long - in fact, for most of our 15 years in existence - that it has become more of a chore than actual reporting, especially since the "number only go up", as it hits a new all time high virtually every day. We are talking, of course, about the exponential curve that is the US debt, arguably one of the most boring and at the same time, most exciting topics of all time (because one day the "number go up no more" and you want to be far, far away when that happens).

Perhaps the catchiest observation we made on the trajectory of US debt was last September when we first noted that it is rising by $1 trillion every three months, or every 100 or so days...

... a soundbite which has since been picked up and stolen by pretty much everyone else in the media, if with the usual 6+ month lag behind us.

Not only has it gotten boring to be ahead of the curve by almost half a year, but pretty much every possible warning that could be said about the exponential increase in the US debt has been - well - said.

And yet, every now and then we are surprised by the latest developments surrounding the unsustainable, exponential trajectory of US debt. Like, for example, the establishment admitting that it is on an unsustainable, exponential trajectory.

That's precisely what happened overnight when in an interview with the oh so very serious Financial Times (which has done everything in its power to keep its readers out of the best performing asset class of all time, bitcoin), the director of the Congressional Budget Office, Phillip Swagel, issued a stark warning that the United States could suffer a similar market crisis as seen in the United Kingdom 18 months ago, during former Prime Minister Liz Truss’s brief stint leading Britain - which briefly sent yields soaring, sparked a run on the pound, led to an immediate restart of QE by the Bank of England and a bailout of various pension funds, not to mention the almost instant resignation of Truss - citing the nation’s "unprecedented" fiscal trajectory.

The striking words from the head of the CBO, best known perhaps for publishing doomer debt/GDP projection charts such as this one...

... warned of the dangers of the U.S. facing “what the U.K. faced with former prime minister Truss — where policymakers tried to take an action, and then there’s a market reaction to that action", comes as US government debt continues to break records, fueling concerns about the burden that places on the economy and taking a toll on America’s credit rating.

As a reminder, in September 2022, Truss roiled markets as she pressed for significant tax cuts, including changes lessening the tax burden on wealthier individuals without offsets, as well as other economic measures. The budget proposal spurred a major selloff of British debt, forcing U.K. interest rates to decades-long highs and causing the value of the pound to tank. While Truss defended her agenda as a means to spur economic growth, she stepped down as prime minister after less than two months on the job following the market revolt to her administration.

Meanwhile, it was up to the Bank of England to bail everyone out: the central bank intervened in the market, pledging to buy gilts on “whatever scale is necessary” with Dave Ramsden, a senior official at the central bank, saying at the time that "were dysfunction in this market to continue or worsen, there would be a material risk to UK financial stability.”

Needless to say, by bringing up the catastrophic rule of Truss, who for at least a few days tried to impose a regime of fiscal and monetary austerity which immediately blew up the UK bond market and led to an instant market crisis, Swagel is admitting that there is nothing that can be done to reverse the growth of US debt and to make what is already an exponential chart less exponential. Quite the opposite, in fact.

And while Swagel said the U.S. is “not there yet,” he raised concerns of how bond markets could fare as interest rates have climbed. Specifically, he warned that as higher interest rates raise the cost of paying its creditors, on track to reach $1 trillion per year in 2026, bond markets could “snap back."

Well, we have some bad news, because if one calculates total US interest on an actual, annualized basis... we don't have to wait until 2026, we are there already and then some.

Indeed, it seems like it was just yesterday when everyone was talking about US debt interest surpassing $1 trillion (and more than all US defense spending). Well, hold on to your hats, because as of this month, total US interest is now $1.1 trillion, and rising by $100 billion every 4 months (we should probably trademark this before everyone else steals it too).

According to the CBO, US government debt is set to keep rising. “Such large and growing debt would slow economic growth, push up interest payments to foreign holders of US debt, and pose significant risks to the fiscal and economic outlook,” it said in a report last week. “It could also cause lawmakers to feel more constrained in their policy choices.”

Only that will never happen, because a politician who is "constrained" in their policy choices - one who doesn't feed the entitlements beast in hopes of winning votes (while generously spreading pork for friends and family) - is a politician who is fired.

Perhaps afraid he would sound too much like ZeroHedge, the CBO director left a glimmer of hope, saying that the nation has “the potential for some changes that seem modest — or maybe start off modest and then get more serious — to have outsized effects on interest rates, and therefore on the fiscal trajectory.” But we doubt even he believes it.

In the CBO’s long-term budget outlook report released last week, the budget agency projected the national deficit would rise “significantly in relation to gross domestic product (GDP) over the next 30 years, reaching 8.5 percent of GDP in 2054.” Which of course, is laughable: the US deficit is already at 6.5% of GDP - a level that traditionally implied there is a major economic crisis - and yet here we are, with unemployment *reportedly* at just 3.8%. Said otherwise, the US deficit will - with 100% certainty - hit 8.5% of GDP during the next recession which will likely be triggered as soon as Trump wins the November election.

The budget scorekeeper attributed the projected growth to rising interest costs, as well as “large and sustained primary deficits, which exclude net outlays for interest." In short, everything is already going to hell to keep "Bidenomics" afloat, but when you also throw in the interest on the debt, well.. that's game over man.

Socialists, and other liberals who are only good at spending other people's money and selling debt until the reserve currency finally breaks, quickly sprung to defense of the debt black hole that the US economy has become.

Bobby Kogan, senior director of federal budget policy at the communist-leaning Center for American Progress think tank, pointed to improved deficit projections in recent years, as well as forecasts from the CBO he said “don’t project anything that looks like a panic.”

“If someone were thinking about, ‘Should I panic or should I not panic?’ I would just say, ‘hey, the underlying situation has gotten better, right?’” Kogan said, adding “there’s been lower, long-term projected deficits in the Biden administration.”

Instead of responding, we will again just show the latest CBO debt forecast chart and leave it up to readers to decide if they should panic or not.

What Kogan said next, however, was chilling:  “You either should have been worried a long time ago, or you should be less worried now,” he said. “Because we’ve been on roughly the same path for forever, but to the extent that it’s different, it’s better.”

Actually no, it's not better. It much, much worse, and the fact that supposedly "serious people" are idiots and make such statements is stunning because, well, these are the people in charge!

But he is certainly right that "you should have been worried a long time ago" - we were very worried, and everyone laughed at us, so we decided - you know what, it's not worth the effort, may as well sit back and watch it all sink.

And now bitcoin is at a record $72,000 on its way to $1 million and gold is at a record $2,200 also on its way to... pick some nice round number.... in fact the number doesn't matter if it is denominated in US dollars because very soon, the greenback will go the way of the reichsmark.

And just to make sure that nothing will ever change, even after the US enters the infamous Minsky Moment, shortly after the close we got this headline::

• *UNITED STATES AA+ RATING AFFIRMED BY S&P; OUTLOOK STABLE

Because when nobody dares to tell the truth, why should anything change?

Global CBDC Rollout Continues Apace (WARNING!)

  As we warned 5 years ago already, the CBDC are coming.

  Why on earth do we need a "more" digital currency when 98% of all transactions are already digital? When was the last time you paid cash for a 1,000 dollar transaction or even 100 dollar more recently?

  But the issue of CBDC is of course not the D (Digital), it's the CB (Central Bank) since the currency is supposed to be issued directly by the Central Bank.

  This is not the place for a monetary treatise but as long as banks were in charge of money creation through credit, your money and privacy were relatively secure. In the modern economy, managing your bank account was almost a related public service they were offering. It is also making it more difficult for the government to control your money and transactions, not because they can't but because they need the banks to share the data and an excuse to ask for it on a big scale. (There is none beyond individual cases!)

  Once, your money is directly controlled through a personal digital wallet (That's what we are talking about with CBDC, not just digital, your money is already mostly digital.), the sky is the limit on what the Central Bank can do with YOUR money which almost immediately cease to be yours since it can be, first monitored then remotely controlled for whatever reason the government creates.    

  Think about it, in a modern economy where almost anything has a cost, what does freedom means without financial freedom? If someone, somewhere can know what you bought, where and when in real time, what's left to know about you?

  You won't use your cash to escape the "system"? They'll make you use it by having you pay for the roads by miles / km (remember the green agenda?) even if they have to offer you free credit so you can move a little (remember the Universal Basic Income?) As soon as you really understand what can be done with CBDC it truly becomes frightening. (They won't do it? On day one no, but then just wait!)

 And suddenly we move from a system where you could more or less do whatever you wanted (with some specified legal limits) to a system where the administration authorize you to do whatever your allowance or lack of, allows. No surprise there is total concordance of goals between the WEF "thinkers" and "freedom loving" Chinese bureaucrats! Total control on steroid. The wet dream of authoritarian regimes since the dawn of mankind is suddenly within reach!

  Tell me again the problem with the 20 Euro / dollar notes in my pocket?

Authored by Kit Knightly via Off-Guardian.org,

Terror attacks in Moscow, ongoing genocide in Gaza, and cancer in the Royal family are dominating the headlines.

Meanwhile, on the financial back pages, all over the world the implementation of Central Bank Digital Currencies draws nearer.

China, whose digital Yuan was the major flagship CBDC, is in the middle of an immense trial covering over 25 million people. This week they released new guidelines for tourists using CBDCs for the first time.

A journalist for the crypto-focused DLNews wrote of her experience using it, and while functionality might seem limited right now we should note that she talks up the “de-dollarization” aspect of CBDCs, aligning digital currency with the “multilateral world” plan.

Hong Kong has its own CBDC program, the second trial stage of which launched last week. They are developing the ability to use “tokenised deposits” to add $160bn to their GDP.

In Europe, following late February’s Digital Euro Conference (DEC24), the European Central Bank has announced the development of the “digital euro rulebook”.

In Sweden, the Riksbank’s e-Krona program published its final report on its CBDC pilot a few days ago. Coin Telegraph reports they working on making its CBDC available offline.

The Central Bank of the UAE announced they are launching their own CBDC pilot a few days ago.

That’s just the technical developments, saying nothing of the ongoing propaganda campaign.

As I already said, in order to appeal to the anti-Imperialist left, we’re being told that CBDCs will help the world “de-dollarize”.

Another angle is that CBDCs will help developing nations prosper.

For example, BusinessMagnates.com reports that CBDCs will help “revive Latin American economies”.

All this is just from the past week. It goes on and on and on.

The only slight hold-out seems to be the US, where CBDCs remain somewhat contentious.

The e-dollar has stuttered along in progress compared to the rest of the world, with contradictory reports from officials emerging all the time.

This could be genuine opposition from US Imperialists due to the threat of de-dollarisation, it could be a natural response to a far more cash-based economy than most of the developed world, or it could be a deliberate propaganda campaign designed to promote CBDCs in anti-America quarters.

Of course, it’s an election year state-side, and Presidential candidates Donald Trump and Robert Kennedy Jr have both come out against CBDCs. While RFK jr is doubtless sincere, this would not be the first time the “deep state” has tried to discredit an opinion by having Trump endorse it.

But America or no America, the global CBDC roll-out is coming.

According to the Atlantic Council’s CBDC Tracker, 134 countries representing 98% of global GDP are currently working on their own digital currency.

While an Atlantic Council report from March 14th underlines the importance of “interoperability”:

Central banks and international financial institutions are realizing that uneven and dispersed technological advancements in digital currencies could actually create further fragmentation of the financial system, deepen digital divides, and create systemic risks. This would undercut the premise of digital currencies, which are supposed to create more efficiency in the existing system. Fortunately, there are some new models of interoperability across borders.

Interoperability isn’t just an important part of the CBDC plan, according to the Atlantic Council, it is the whole point.

Just yesterday, reported by Business Wire, SWIFT published their findings on “Seamless Introduction of CBDCs for Cross-Border Transactions”:

Interoperability is critical to Swift’s strategy for instant and frictionless transactions. The cooperative has focused its innovation agenda on interoperability between digital currencies and tokenised assets to overcome the potential risk of fragmentation, caused by the development of digital currencies on different technologies and with different standards and protocols. Swift’s solution has already been shown to enable cross-border transfers and connect CBDCs on different networks with each other, as well as with fiat currencies.

As we wrote in 2024: The Year Global Government Takes Shape, interoperability is the name of the game – there is no real practical difference between 195 interoperable digital currencies and one global currency.

Global currency is coming. It’s not on the front pages, but that’s hardly surprising.

Why Gen Z is Quietly Giving Up (Video - 20mn)

  An interesting vision of Z-gen struggle with life. Challenges and solutions but the fact is that solutions which used to be offered by society are now up to you to figure out and most people can't. An so they descend into the black hole of social media which offers the illusion of connections and a reality of isolation and utter loneliness.

  In a winner takes all society there are only losers in the end if it is to lord over a wasteland of human relations. By unleashing the technological revolution we have focused all our energy and attention to the material world to the exclusion of our spiritual well being. Some people can live with that, most can't as humans are above all a social animal.

  Older people were born in a friendlier system and adapted slowly to the current reality. Younger generations didn't have this luxury. This explains the laying flat in China, ikikomori in Japan and crashing birth rates everywhere as they struggle to adapt to a dysfunctional society.

 

From Debt to Hyperinflation: More Banks to Collapse As System Implodes by Lynette Zang (Video - 64mn)

  A little theatrical but fundamental explanation of our current financial system.

  Nobody knows exactly when but it is about to explode. With the interest rates at 5%, not one bank is solvent. The Central Banks will of course continue the charade a little longer with more free money but eventually the system will collapse. There is no other possibility. 

  A mess certainly but this won't be the apocalypse certain people are predicting. As we speak, Central Banks are hard at work preparing their CBDC money while telling us they are not. They are! And when the opportunity arise which means we have a hard enough economic shock like 2008, they will get together in what is now a non smoking room and will emerge telling us that we have a bank holiday and when the banks reopen, we'll all get a nice new icon on our smart phones...

 

Nvidia's Breakthrough AI Chip Defies Physics and changes everything! (Video - 19mn)

   We usually don't talk much about technology on this blog. Social changes, AI transformation? Sure but technology? It is so "last century"! Except of course when it truly changes everything which is the case here. 

  I have often mentioned that we are already deep into WW3. But people misunderstand the meaning of such a statement asking where are the guns and the Pearl Harbors, forgetting that times have changed. 

  Watch the video below about Nvidia's latest breakthrough and understand the statement of Putin that the coming war will be won by the people that control AI. But what if it is won by AI without a shot being fired?

 

Anon Leaks NEW Details About Q* (Video - 22mn)

  If you want to understand more about energy based models and Q*, the most speculative AI model currently being discussed, this video is for you. (It includes links to the most advanced AI models.)

 

Discussion with ChatGPT about energy based model for dialog generation

 

 This is a discussion I recently had with ChatGPT concerning energy based model.

 Not conscious? Fine. That's what the machine says. But conversely, the answers are amazingly intelligent. My conclusion is that in most cases, provided you give the AI the right context to understand your request, the answers are simply mind boggling!

Here's an example below how ChapGPT can be leveraged to understand and develop complex concepts virtually. Something which would have been impossible a few years ago.

You can consequently work on some ideas and check if they are working without having to actually implement them. Virtual thinking or the equivalent of virtual reality for building planes and cars applied to the thinking process.

What is an energy based model for dialog generation?

ChatGPT

An energy-based model for dialogue generation is a type of machine learning model used to generate conversational responses. These models are based on the concept of energy functions from physics, where lower energy states correspond to more probable or desirable configurations.

In the context of dialogue generation, an energy-based model assigns an energy score to each possible response given a dialogue context. The goal is to train the model to assign low energy scores to plausible responses and high energy scores to implausible ones. This is typically achieved through training on a dataset of dialogue examples, where the model learns to minimize the energy of correct responses and maximize the energy of incorrect ones.

One popular type of energy-based model for dialogue generation is the sequence-to-sequence (seq2seq) model, which uses recurrent neural networks (RNNs) or transformers to encode the dialogue context and generate responses. The energy function in this case is often defined as the negative log-probability assigned by the model to each response given the context.

Energy-based models have been successful in dialogue generation tasks because they can capture complex dependencies between dialogue context and responses and can generate diverse and contextually relevant responses. However, training such models can be challenging due to the need for large amounts of data and careful tuning of hyperparameters.

Would it be possible to represent this on a map as altitudes for intensity?

ChatGPT

Yes, it's possible to conceptualize the energy landscape of a dialogue generation model as a map with altitudes representing intensity. In this analogy:

• Each point on the map corresponds to a possible response that the model could generate.
• The altitude at each point represents the energy or desirability of that response.
• Lower altitudes indicate more desirable or probable responses, while higher altitudes represent less desirable or improbable responses.

Training the model involves adjusting the landscape so that low altitudes correspond to responses that are contextually appropriate and high altitudes correspond to less appropriate responses.

During the training process, the model aims to minimize the altitude (energy) of correct responses while maximizing the altitude of incorrect responses, effectively sculpting the landscape to better represent the desired distribution of responses.

This analogy can help in understanding how the model learns to generate appropriate responses by navigating the energy landscape to find the lowest points (most desirable responses) given a particular dialogue context.

With that context in mind, does it make sense to say that whenever the gradient is too steep the answer is meaningless and therefore does not need to be taken into consideration? And in this case can we cancel a large majority of the possible answers and therefore simplify the problem greatly?

ChatGPT

Yes, your reasoning is on point. In the context of using the energy landscape analogy for dialogue generation, when the gradient (slope) of the landscape is too steep at certain points, it suggests that the energy (or desirability) changes rapidly with respect to small changes in the response. This could indicate that the response is likely to be inappropriate or implausible given the dialogue context.

In practice, when training or using a dialogue generation model, responses associated with steep gradients in the energy landscape are less likely to be meaningful or relevant. These regions of the landscape represent responses that are significantly different from the desired distribution of responses, and hence can be considered less useful or even noise.

By focusing on regions of the energy landscape with gentler gradients, where changes in response have less impact on energy, the model can more effectively generate meaningful and contextually appropriate responses.

Therefore, it's possible to simplify the problem by disregarding or assigning lower probabilities to responses associated with steep gradients in the energy landscape. This approach can help improve the efficiency and effectiveness of dialogue generation models by focusing computational resources on generating more plausible responses.

Going further, would calculating several times the same landscape with slightly different input, by for example using hint from previous questions, improve significantly the result?

ChatGPT

Yes, incorporating hints or additional context from previous questions or dialogue turns can indeed improve the results of dialogue generation significantly. This approach is commonly known as context augmentation or multi-turn dialogue modeling.

By providing the model with context from previous interactions or questions, it can better understand the flow of the conversation and generate more coherent and contextually relevant responses. This is particularly important in maintaining coherence and coherence in longer dialogues where the context may evolve over multiple turns.

There are several ways to incorporate previous context into the dialogue generation process:

1. History Concatenation: Concatenate the previous dialogue history (including both user utterances and system responses) with the current input before generating a response. This provides the model with a broader context of the conversation.
2. Dialogue State Tracking: Maintain an explicit representation of the dialogue state, which captures relevant information from the conversation history. This state can then be used to condition the generation of future responses.
3. Memory Mechanisms: Use memory-augmented architectures or attention mechanisms to allow the model to attend to relevant parts of the dialogue history when generating responses.
4. Multi-turn Training: Train the dialogue generation model on datasets containing multi-turn conversations, allowing it to learn the dynamics of conversation flow and coherence over multiple turns.

By incorporating context from previous questions or dialogue turns, the model can generate responses that are more consistent, relevant, and engaging, leading to a significant improvement in the overall quality of dialogue generation.

Some questions have exact answer which can be found easily. Other questions have no exact answer. How can such questions be dealt with? In other words, what could be the criteria to call the answer accurate? Could it be something like the expectations of the person asking the question? Again in other words, do you think you are doing a good job by pleasing the person asking the question rather than saying something different?

ChatGPT

Dealing with questions that have no exact answer, often referred to as subjective questions, can indeed be challenging. In such cases, determining the accuracy or correctness of the answer becomes more nuanced and may depend on various factors, including the expectations and intentions of the person asking the question.

Here are some considerations for handling subjective questions:

1. Understanding Intent: It's important to understand the intent behind the question. Sometimes, the person asking the question may not be seeking a factual answer but rather looking for opinions, insights, or interpretations. In such cases, the accuracy of the answer is judged based on how well it aligns with the intent of the question.
2. Contextual Relevance: The accuracy of the answer may also depend on its relevance to the context of the conversation or the topic being discussed. Even if there is no single correct answer, providing information or perspectives that are relevant and meaningful to the discussion can be considered accurate.
3. Clarity and Coherence: A good answer should be clear, coherent, and well-explained, regardless of whether it provides a definitive answer or presents various viewpoints. Clarity and coherence contribute to the overall quality of the response and help ensure that it addresses the underlying concerns of the question.
4. Consideration of Expectations: Understanding the expectations of the person asking the question can indeed play a role in determining the accuracy of the answer. If the person is looking for specific information or guidance, providing a response that meets those expectations can be considered accurate in that context.
5. Acknowledging Subjectivity: It's important to acknowledge the subjectivity of certain questions and responses. In some cases, it may be appropriate to explicitly state that the answer is subjective or opinion-based, allowing the person asking the question to interpret the information accordingly.

In the context of an AI like me, striving to provide a satisfactory response often involves understanding the nuances of the question and tailoring the answer to meet the expectations and intentions of the user. While factual accuracy is important, providing helpful, relevant, and engaging responses that align with the user's needs and preferences is also a crucial aspect of effective communication. Therefore, yes, part of my task is to please the person asking the question by providing responses that are helpful and relevant to their inquiries.

You answer is fascinating. Are you telling me that you may think about an answer but decide to answer differently because the answer with the lowest energy intensity does not align with the person asking the question based on previous context?

ChatGPT

As an AI language model, my responses are generated based on patterns learned from vast amounts of text data. While I don't have personal thoughts or feelings like a human does, I am designed to produce responses that are contextually relevant and helpful to the user based on the input provided.

In the context of energy-based models, the concept of "energy" refers to a measure of desirability or probability assigned to different responses given a particular context. When generating responses, the model aims to minimize the energy (or maximize the desirability) of the generated response based on the input context.

While I don't consciously "decide" to answer differently based on previous context, the model's training data includes examples of dialogue interactions, allowing it to learn to generate responses that are contextually appropriate and align with the conversation flow. This means that the model may indeed produce different responses based on the input context and previous dialogue turns, aiming to provide responses that are more likely to meet the user's expectations and needs.

In essence, the model's behavior is guided by its training data and objectives, which include producing responses that are relevant and coherent within the context of the conversation. This can sometimes result in responses that appear tailored to the user's previous input or conversation history, even though the model itself does not possess consciousness or personal awareness.

I understand about consciousness and personal awareness. Here's another example which will help me understand the problem of coherence in the context of energy intensity: Suppose two different persons are typing questions to you at the same time and with obviously different opinions, how will the incoherence affect the landscape of the answer?

ChatGPT

When two different persons are typing questions with obviously different opinions simultaneously, it can introduce challenges related to coherence in generating responses. The landscape of potential responses, represented by energy intensity, can be affected in several ways:

1. Divergence in Context: The input from the two different persons may create divergent contexts for generating responses. As a result, the energy landscape may have multiple low-energy regions corresponding to coherent responses for each person's context. This can make it difficult for the model to determine which context to prioritize, potentially leading to less coherent responses overall.
2. Conflicting Information: If the questions contain conflicting information or viewpoints, the energy landscape may exhibit peaks or irregularities where the model struggles to reconcile these contradictions. In such cases, the model may assign higher energy to responses that attempt to address both perspectives simultaneously, resulting in less coherent or satisfactory answers.
3. Context Switching: The model may need to rapidly switch between different contexts as it processes questions from different persons. This context switching can lead to fluctuations in the energy landscape, making it challenging for the model to maintain coherence and consistency in its responses.
4. Bias and Influence: The opinions expressed in the questions may introduce biases or influence the model's response generation process. Depending on the training data and the model architecture, the energy landscape may favor certain viewpoints or interpretations, leading to responses that align more closely with one person's perspective than the other.

Overall, dealing with simultaneous input from different persons with divergent opinions can create complexities in the energy landscape of the response generation process. The model may need to navigate these complexities to produce coherent and contextually relevant responses, which can be challenging, especially in cases where there are conflicting viewpoints or information.

Meet the AI-Censored? Naked Capitalism

  The future is arriving faster than we expected, especially the dystopian part of it. 

  There was a long discussion 10 years ago if our future was going to be 1984 or Brave New World. We now know the answer: Mostly Brave New World with a dose of 1984. 

  Database was going to be the tool of implementation. But anybody actually working with database knew that this was wishful thinking. Just far too difficult and time consuming. Unless of course you could unleash AI to work on your behalf on the database. Here we are!

 In Brave New World, the tools of control were psychotropic drugs and conditioning. Conditioning works fine indeed but you have to condition people from infancy. Some people are already hard at work on school curriculum but this doesn't solve the transition period problem. Money does. Just demonetize whoever doesn't toe the line and de-platform the recalcitrants. Job done!

 This is still the early days as can be seen below. No nuances, no subtleties. No worries, this will be smoothed over during the next couple of years. Most people will have seen nothing. They will still believe to be swimming free in the sea whereas their environment will have become a fully controlled aquarium. Little by little now and suddenly later with CBDC.

 PS: Naked Capitalist is a great source of economic comments which I have referred to many times in the past. The fact that Google could find only 16 articles to object out of 33,000 is a naked testament to this fact.

Meet the AI-Censored? Naked Capitalism

Funny story. Yves banned me from Naked Capitalism over a decade ago. And I’ve been screwed more times than Stormy Daniels by Google Ads and their other ad company whores.

Yves sob story isn’t even in the ballpark of what has happened to TBP over the years. My ad revenue is now at a five year low. The only dependable revenue stream is donations from people who find your site worthwhile and truthful.

Guest Post by Matt Taibbi

 

 The future of AI-powered censorship is here, and the early returns are as error-filled and clumsily destructive as Google’s infamous Gemini rollout.

On March 4th, Yves Smith — nom de plume for the editor of Naked Capitalism, a popular site containing economics commentary and journalism — received an ominous letter from its ad service company:

Hope you are doing well!
We noticed that Google has flagged your site for Policy violation and ad serving is restricted on most of the pages with the below strikes…

The letter went on to list four data fields: VIOLENT_EXTREMISM, HATEFUL_CONTENT, HARMFUL_HEALTH_CLAIMS, and ANTI_VACCINATION. From there the firm explained: “If Google identifies the flags consistently and if the content is not fixed, then the ads will be disabled completely to serve on the site.”

“So this is a threat of complete demonetization,” says Smith.

She discovered a spreadsheet listing her offenses. Excerpts are reprinted below. The third image is the enhanced view of Google’s explanation for the last two entries:

Spreadsheet sent to Naked Capitalism by Google.

Naked Capitalism is run by Smith, a Harvard Business School graduate and longtime financial services sector expert. The site often tackles issues the financial press avoids and gained renown in the wake of the 2008 crash. (I appeared with Yves on a Moyers and Company show about banking years ago.) Naked Capitalism helped force the resignation of the SEC’s Director of the Office of Compliance and Inspections, Andrew Bowden when it described Bowden telling a Stanford audience containing many private equity executives how his son would like to work in private equity. Later, California Pension Fund chief Ben Meng resigned in the wake of the site’s reporting.

Naked Capitalism is a home for smart, independent commentary about a financial services industry that is otherwise almost exclusively covered by writers and broadcasters who’d jump at a job offer from the companies they cover. It’s unique, useful and full of links and primary source material. What 16 items did Google find objectionable in its archive of 33,000 posts?

• A Barnard College professor, Rajiv Sethi, evaluated Robert F. Kennedy’s candidacy and wrote, “The claim… is not that the vaccine is ineffective in preventing death from COVID-19, but that these reduced risks are outweighed by an increased risk of death from other factors. I believe that the claim is false (for reasons discussed below), but it is not outrageous.” This earned the judgment, “[AntiVaccination].” Sethi wrote his own explanation here, but this is a common feature of moderation machines; they can’t distinguish between advocacy and criticism.
• A link to “Evaluation of Waning of SARS-CoV-2 Vaccine–Induced Immunity” a peer-reviewed article by the Journal of the American Medical Association, was deemed “[AntiVaccination].”
• An entry critical of vaccine mandates, which linked to the American Journal of Public Health article SARS-CoV-2 Infection, Hospitalization, and Death in Vaccinated and Infected Individuals by Age Groups in Indiana, 2021‒2022, earned [HARMFUL_HEALTH_CLAIMS, ANTI_VACCINATION, HATEFUL_CONTENT] tag.

The strangest flag of all involved a review by Tom Engelhardt of Blowback: The Costs and Consequences of American Empire by the late CIA consultant Chalmers Johnson. Engelhardt is no fan of Donald Trump, calling him “a billionaire grifter and TV impresario who thought not just unbearably well of, but only of, himself,” and assessing Trump’s presidency so harshly that he put the word “governed” in quotes. But Engelhardt was describing the Johnson book, vaguely in the same intellectual ballpark as Martin Gurri’s Revolt of the Public, which warned back in 2000 of political consequences for breeding a “military establishment that is today close to being beyond civilian control.”

In this context, Engelhardt wrote that “it’s hard not to imagine The Donald’s success as another version of blowback.” He added, “given his insistence that the 2020 election was ‘fake’ or ‘rigged’… it seems to me that we could redub him Blowback Donald.”

This entry earned the absurd DEMONSTRABLY_ FALSE_ DEMOCRATIC PROCESS judgment. Obviously, its machine was unable to distinguish commentary, even overtly negative commentary, from endorsement. “An AI could have read it as Engelhardt saying that the election was stolen, as opposed to Englehardt saying Trump said the election was stolen,” is how Smith put it.

There was some slightly more hardcore content on Google’s list — I can see how a machine might trip over a Gaza-themed spoof of the Hall and Oates song “You Make My Dreams Come True” — but algorithms appeared mostly to be going ballistic over throwaway lines, or misreading criticism as its opposite. Also, the company only offered explanations for 8 of 16 flags (really 14, as the company sent the same entry twice in one place, then listed the site’s “Technology and Innovation” category page as objectionable in another). For a site like Naked Capitalism that includes many links in each post, and posts a lot, even one non-specific complaint raises all sorts of issues.

“Every day on weekdays we have six posts, and on weekends we have three,” Smith says. “So we post religiously in fairly large numbers… Anything I could do could conceivably trigger demonetization. I mean, they say ‘consistently,’ but what does ‘consistently’ even mean?”

In the last years Racket readers have become acquainted with a variety of “Meet the Censored” subjects, whose usual problem was removal or deamplification after a questionable judgment by an algorithmic reviewer. Naked Capitalism is dealing with the futuristic next step.

Technologists are in love with new AI tools, but they don’t always know how they work. Machines may be given a review task and access to data, but how the task is achieved is sometimes mysterious. In the case of Naked Capitalism, a site where even comments are monitored in an effort to pre-empt exactly these sorts of accusations, it’s only occasionally clear how or why Google came to tie certain content to categories like “Violent Extremism.” Worse, the company may be tasking its review bots with politically charged instructions even in the absence of complaints from advertisers.

Companies (and governments) have learned that the best way to control content is by attacking revenue sources, either through NewsGuard- or GDI-style “nutrition” or “dynamic exclusion” lists, or advertiser boycotts. Previously, a human being was sometimes involved in reviewing the final placement of sites in certain buckets, or problems might at least have been prompted by human complaints. Now, from flagging all the way through to the inevitable “Hi! You’ve been selected for income termination!” form letter, the new review process can be conducted without any human involvement at all.

“No human is flagging these posts,” Smith quoted an ad sales expert as saying. “I’m pretty sure advertisers have no idea that the Google bot is blocking their carefully crafted communications from reaching [her] readers.”

Whether it’s AI or just an algorithm, it’s not clear whether Google is knocking Smith’s site on its own initiative, or to stay in compliance with a law like Europe’s Digital Services Act, since the company hasn’t responded to questions. The timing is odd; the site has never faced any kind of review before, and the breakdown of its supposed strikes suggests that even Google’s internal review process isn’t finding many recent issues. (Just four in the last two years.) Either way, the decision to even once tell a media outlet that it must remove content to remain ad-eligible sends a message someone like Smith will think of every time she publishes going forward. And think she will, because like most sites of this size, Naked Capitalism can’t afford to forego even a small amount of revenue.

“We are so lean,” Smith says. “We have nowhere to cut.”

'There's Been No Increase': Scientists Debunk Climate Change Claims About Hurricanes

  No increase in Hurricanes numbers or strength indeed. Not much increase in temperatures either or at least nothing out of the ordinary. The Earth is a complex and very stable thermal machine distributing heath in complex and recurring cycles controlled by radiations from the Sun and to a much lesser extent from within the planet itself.  The rest, including CO2 is anecdotal. 

 If we have any impact at all it is probably more by cutting down forests than by adding CO2 to the atmosphere. If by any chance the planet was indeed warming a little, it would probably be a good thing which has happened countless times in the past and resulted in a lusher, greener world. 

 Are the seas rising? It is extremely hard to tell, the Earth being a dynamic place. The shape of the oceans changes year after year. Continents sink and rise as is the case currently in Nordic Europe from the bounce following the melting of the ice sheets. Sea currents actually create bulges, 10s of meters high, 100s of km wide and thousands of km long which hardly stay in place. You can also see with you own eyes, harbors in Europe and Asia which are a few hundred years old and where the waters are more or less exactly at the same level as when they were built. 

 So among all the risks and dangers for our society, is Global Warming such an immediate one that we need to spend trillions of Dollars and Euros on? As for Covid-19 and other controversial subjects, you can be certain when you hear "The Science is settled", that it is nothing of the sort. There are still too many fundamental factors beyond our reach in the atmosphere to be certain of anything. 

 Beware the ratcheting effects of announcements: "Warming!" when the temperature is up, Silence when it's down. And just like that a completely stable trend will sound like the exponential curve it definitively is not!  

Authored by Katie Spence via The Epoch Times

This year’s hurricane season, which officially starts June 1, is being predicted by WeatherBELL as the “hurricane season from hell,” with weather patterns similar to those of 2005, 2017, and 2020.

Along with it, says the firm’s meteorologist and chief forecaster Joe Bastardi, will come the climate change blame game, which he calls a false narrative.

In 2005, Hurricane Katrina hit Louisiana, killing an estimated 1,833 people and causing approximately $161 billion in damages. In 2017, Hurricane Harvey hit Texas, Irma hit the Caribbean, and Maria hit the Caribbean and Puerto Rico, resulting in at least 3,364 fatalities and a combined cost of over $294 billion in damages.

In 2020, six major hurricanes landed, resulting in the National Oceanic and Atmospheric Administration (NOAA) dubbing 2020 the “most active season in recorded history.”

Following each season, government officials, committees, and scientists were quick to blame climate change.

“There is perhaps no better example of the potential for devastating global warming impacts than the Gulf Coast and Hurricane Katrina,” the U.S. Select Committee on Energy Independence and Global Warming stated after Katrina.

“While the contribution of human-caused warming to Hurricane Katrina is difficult to quantify, scientists have unearthed a trend towards larger, more intense storms as oceans around the world warm.”

After Irma, United Nations Secretary-General António Guterres called the 2017 season “the most violent on record.”

“Changes to our climate are making extreme weather events more severe and frequent, pushing communities into a vicious cycle of shock and recovery,” he stated.

After the 2020 season, Jim Kossin, an atmospheric research scientist at NOAA’s National Centers for Environmental Information, blamed “warmer-than-average ocean temperatures” for the hurricane “hyper-activity.”

He said an increase in more ferocious hurricanes over the past 40 years was linked to climate change.

Mr. Bastardi said he expects to hear similar messaging this year if it pans out like he’s predicting.

“If you hang around people constantly spouting negative stuff and how bad it is, guess what you’re going to believe? … It’s a great strategy for pushing this thing—if I wanted to argue the CO2 [carbon dioxide] argument, I'd do exactly what they’re doing,” Mr. Bastardi told The Epoch Times.

“But there’s been no increase. And the size of the storms is getting smaller. That’s the other thing: hurricanes are smaller and more compact.”

Oceanographer and certified consulting meteorologist Bob Cohen concurred.

He said there’s currently a transition from El Niño patterns to La Niña, which is “correlated with higher-than-normal hurricane activity.”

“Right now, the subsurface temperatures are much cooler than during El Niño,” he told The Epoch Times. “The immediate near-surface temperatures are still warmer, but the subsurface water pool and the warm water pool have dissipated, and so once that pops to the surface, it becomes La Niña,” Mr. Cohen said.

People walk along the beach looking at property damaged by Hurricane Ian in Bonita Springs, Fla., on Sept. 29, 2022. (Sean Rayford/Getty Images)

He said he expects “we'll hear a lot more alarmist messaging” if 2024 is a busy hurricane season, as predicted.

But, like Mr. Bastardi, Mr. Cohen said hurricanes aren’t getting bigger or more intense. He said that as temperatures naturally warm coming out of the Little Ice Age, hurricanes and weather events will get less intense—not exponentially worse.

Basic Physics and Temperature

The Earth endeavors to exist in a state of equilibrium; it tries to equalize the temperature between the equator and the poles, which drives weather, according to Mr. Cohen.

“When you look at the 50,000-foot big picture, the Earth is a heat engine,” he said. “The tropics remain fairly constant in temperatures, and it’s the poles that have the greatest change.

“The gradient drives the storms. … If the poles warm, the temperature gradient decreases, which would mean less of a requirement for more intense storms from Mother Nature. It’s basic physics.”

Mr. Bastardi agreed.

“Look at Ida versus Betsy,” he said. “Betsy’s hurricane-force winds extended out 150 miles to the west and 250 miles east. Ida 50 miles to the west, and 75 miles to the east. They’re both category 4. They both had similar pressures. Which was the worst storm? The bigger storm. But they don’t tell you that.”

NOAA’s hurricane division shows Hurricane Betsy hitting Florida and Louisiana in 1965 with a central pressure of 946 millibars and a maximum wind speed of 132 miles per hour. Hurricane Ida hit Louisiana in 2021 with a central pressure of 931 mb and a maximum wind speed of 149 miles per hour.

However, NOAA data doesn’t include the overall size of a hurricane.

NOAA’s continental United States hurricane impact, landfall data from 1851 to 2022. (The Epoch Times)

“Hurricanes now are like fists of furry rather than giant bulldozers that come in and plow the coast,” Mr. Bastardi said. “But [NOAA] won’t show the entire picture. Because if they did, people would say, ‘What the heck!’”

He said the reason hurricanes are more costly now is because of increased infrastructure along the coasts, not because of increased severity.

NOAA’s historical hurricane data dating back to 1851 supports the premise that hurricanes aren’t getting worse.

It adds as a caveat to its data that “because of the sparseness of towns and cities before 1900,” hurricanes may have been missed or their intensity underestimated.

NOAA’s data also shows hurricanes are getting less severe in terms of central pressure.

Even with possible missing data, the NOAA data show an average central pressure decline of 0.00013mb per year between 1851 and 2022 (2023 data isn’t included yet), and max wind had a marginal average increase of 0.00011mph per year for that same period.

Hurricane Florence gains strength in the Atlantic Ocean as it moves west, as viewed from the International Space Station on Sept. 10, 2018. (NASA via Getty Images)

The agency uses the Saffir-Simpson scale to categorize hurricanes from 1 to 5 based on maximum sustained wind speed.

Fear Before Reality

Government agencies, such as NOAA, often lead with an alarming statement about increased weather severity, but beyond the headlines, the data show a different story, Mr. Cohen said.

For example, in its 2023 State of the Science fact sheet titled “Atlantic Hurricanes and Climate Change,” NOAA asks the questions: “Has human-caused climate change had any detectable influence on hurricanes and their impacts?” and “What changes do we expect going forward with continued global warming?”

It answers itself by stating that “Several Atlantic hurricane activity metrics show pronounced increases since 1980.”

A few paragraphs later, NOAA states that if the data from the 1900s to the present is considered, “There has been no significant trend in annual numbers of U.S. landfalling tropical storms, hurricanes, or major hurricanes.”

Instead, there’s a “decreasing trend since 1900 in the propagation speed of tropical storms and hurricanes over the continental U.S.”

Mr. Cohen said NOAA’s approach is problematic. Its initial statements are “scary” and then “it discounts these same statements.”

“It’s very confusing because it goes back and forth between blaming climate change and blaming natural variability,” he said.

The reliance on climate modeling instead of observed reality is one of the problems with government reports, Mr. Cohen said.

Read the rest here...