Mindmapping The Future

by | Jun 9, 2024 | AI, ChatGPT, singularity

What happens in the next five years?

– AI gets massively smarter and more capable

– Probability – 90%

– Based on the statements of pretty much everyone working in the field, Altman, Ilya, Musk, Gates, Kurzweil, Hassabis, LeCun, and including those like Hinton, Wolfram, etc who have no direct skin in the game

– Even if it isn’t 100% LLM (which I doubt it will be) and includes interconnections with specialist systems using symbolic logic and/or other approaches

– Quite a few people who are involved in AI are predicting AGI by 2027.

– What does the world look like when we have machines that are smarter than every expert human in every domain and are available to everyone for $20 a month?

The answer is WE DON’T KNOW. We cannot predict. And when we have arrived at a place where we honestly can’t predict what life will look like in five years, that, by definition, is a technological singularity.

– We cannot predict, but we can make some educated guesses.

– Businesses will try to use AI to increase profits

– When?

– When AI becomes more reliable, which Altman and others are saying with confidence will happen with GPT5, due out this year

– It’ll start slowly, then go very quickly

The first layer will be tasks that are low risk / high cost / benefit

– 2025-26

– Coding (with humans overseeing / checking the code)

– Customer service (web only, then voice, then retail)

– Analysts (with humans overseeing)

– Writers (PR, journalists, marketing)

– Graphic design

– Industrial design

– The biggest short term impact will be just the explosion of intelligence. Imagine a world where PhD level intelligences are available for $20 a month. What will businesses do with all of that intelligence? A million new scientists to solve our biggest problems, reading and analysing all of the research, developing new trials, running those trials in virtual environments, presenting the best vectors to humans for lab experiments. Imagine a million new scientists hitting the world overnight. (https://cameronreilly.com/a-million-new-everythings/)

The second layer will start to happen when there is confidence in AI capabilities from the experience with the first layer

– 2027-2030

– AGI might arrive around this time, too

– Higher level jobs will start to be replaced

– middle management (because there will be less people to manage)

– legal

– accounting

– HR (again, less people to hire / manage)

– recruitment

– psychologists – everyone has a free AI therapist who knows you more intimately than your own family

– medical – everyone has a free GP

– business strategy

– animation

– acting / film and tv production (as more and more is done with AI)

The third layer will come with cost-effective humaniod robots

– 2030-2040

– manual labour in mines, factories, workshops, maintenance

– When?

– When the TCO of a robot is cheaper than a human

– A labourer costs how much? $50 – 150K a year, depending on the industry?

– A robot will last how many years? 10?

– When you can buy a robot for <$500K, it becomes economically viable.

– Goldman Sachs:

– [“The total addressable market for humanoid robots is projected to reach $38 billion by 2035, up more than sixfold from a previous projection of $6 billion”](https://www.goldmansachs.com/intelligence/pages/the-global-market-for-robots-could-reach-38-billion-by-2035.html)

– [“The manufacturing cost of humanoid robots has dropped — from a range that ran between an estimated $50,000 (for lower-end models) and $250,000 (for state-of-the art versions) per unit last year, to a range of between $30,000 and $150,000 now. Where our analysts had expected a decline of 15-20% per annum, the cost declined 40%.”](https://www.goldmansachs.com/intelligence/pages/the-global-market-for-robots-could-reach-38-billion-by-2035.html)

– “The team’s base case is for more than 250,000 humanoid robot shipments in 2030, almost all of which would be for industrial use. Our analysts’ base case is for consumer robot sales to ramp up quickly over the next decade, exceeding a million units annually in just over a decade.”

– [“In December 2023, billionaire venture capitalist Vinod Khosla made this prediction.](https://www.linkedin.com/pulse/humanoid-robots-here-soon-millions-billions-them-peter-h-diamandis-wdgne/)

“By 2040 there could be a billion bipedal robots doing a wide range of tasks including fine manipulation. We could free humans from the slavery of the bottom 50% of really undesirable jobs like assembly line and farm workers. This could be a larger industry than the auto industry.””

“Robohub, a nonprofit robotics organization, provides a perspective on this. They argue that the “holy grail” for humanoid robots would be crafting sophisticated tech under a $50,000 price tag.

This figure isn’t arbitrary—it aligns with the annual wage of a single shift of labor at just over $18/hour, resonating with the ongoing labor shortages in low-wage industries.

On the other hand, Macquarie dives deep into the cost breakdown for early-stage humanoid robots. Their estimate? A slightly more optimistic $40,000. With allocations like $10,000 for sensors and chips, $5,000 for torque sensors, and $8,000 for precision reducers, they’ve dissected the cost matrix intricately.”`

– Of course, by 2035, many people will be out of work, so who will be able to afford a robot?

– unless… we have not-for-profit robot factories, staffed by robots, making other robots, the costs fall dramatically

– and AI helps us develop nanotechnology, so we can have tiny robots breaking down waste products into their molecular components (oxygen, carbon, hydrogen, nitrogen, silicon, copper, iron) and then building new components out of them

– every home has their own nanofabricator and the first thing you do when you get one is make one for your neighbour

How will businesses use AI?

– Improved customer service experiences

– AI agents know more about the company, more about the customer, are cheaper to run, faster, better at customer relations, can have whatever accent / speak whatever language the customer prefers (no more complains about Indians, etc)

– Reduce employee headcount

– Less managers required

– Less administration required

– Less coders required

– Less people-facing people required

– AI agents can have conversations / take orders / make sales calls with far high efficiency than humans (either voice only, email, or realistic human avatars in a video call)

– What do people do that machines (AI + robots) can’t do?

– Less teachers required

– When / How will unions get involved?

– What about white collar workers who aren’t unionised?

– Governments will try to use AI to reduce costs, improve services

– People will use AI to keep their jobs, in their personal lives until their jobs have been replaced with AI

– What happens when people start losing their jobs?

– High unemployment

– Less cash in the economy

– Business will suffer as there is a cash squeeze

Governments have to intervene to stop economies from collapsing

– Using the usual economic tools – interest rates, printing money, handouts

– AI tax on corporations, goes to UBI / welfare

– Does that create a disincentive on corporations to replace workers in the first place?

– But it will happen in stages, first the jobs will be replaced, the governments will be slow to react

– As people lose their jobs they will become angry – at corporations, at governments, at technology companies

– The property market will implode as people are forced to sell their houses

– Share market will tumble as people pull money out and businesses struggle with less cash in the economy

What holds back adoption of most technological revolutions?

– business / consumer apathy – the market just doesn’t care as much as the tech companies think they will or has a downright negative reaction, eg Google Glass

– doesn’t apply to AI, everyone wants it

– Cost – products are just too expensive to gain enough traction, eg Segway

– consumer level will be low cost / free services (eg iPhone)

– business will justify it by reducing headcount

– Requires people to change behaviours / habits, learning curve too difficult, cost to benefit ratio too high

– AI will have a very low learning curve, it speaks natural language, and will teach you how to interact with it by suggesting prompts

– Will economies with greater government controls, eg China, fare better?

Some people will learn how to use AI to be smarter

– Analyse legal documents to avoid falling into traps with insurance, finance, employment, etc

– Analyse politicians speeches, bills in front of Parliament, news stories

– Organisations (business, political, etc) will use AI to create more propaganda / lies

– But some people will be able to use AI to see through it

– However many won’t use it that way

– AI tools will be built into our every day devices

– from our phones and computers to our Roomba, car, etc.

– Low cost, just a chip which connects to a cloud LLM or runs locally, small footprint model

– Mega Corporations will try to offer their own LLM, eg General Motors, to control the user experience, and will burn billions of dollars, and ultimately fail

Your personal computing device will be your dominant AI agent

– It will be your intermediary with the world

– It will read your emails, text messages, watch / record / save / analyse what you’re doing during the day (both on your devices as well as IRL), listen to your calls, your conversations, etc, and it will all be stored online, backed up, indexed for retrieval.

– People might scream about privacy issues – but we’ve been here before (CCTV, cookies, mobile phones tracking us, credit cards online) and what we’ve learned is that people will trade privacy for convenience, services and benefits if the trade-off seems beneficial

– “I’m not committing any crimes, so what do I care?”

What are the implications?

– Legal – people will have access to video / audio recordings of every interaction, every conversation

– Employers might have access to your recordings made during work hours – but you also have access to all of your conversations with them and colleagues and customers

– The End of Deception?

– Nobody will be able to lie and get away with it

– “Oh my AI was turned off” will be as suspicious as cops turning off their body cam

– Infidelity

– Crime

– What if the cops get an alert when someone turns off their AI monitoring device?

– “Sir, why was your AI turned off at 11pm on the night of January 2?”

– Will wearing an AI device become mandatory?

– We could do that already with some kind of audio/video recorder.

– Courts / police will have access to most recordings for trials

– Marital – spouses will demand access to each other’s recordings

– Arguments about who said / did what will disappear

– But will be replaced by “it’s what I *meant*”, even if it’s not what I *said*”

– It will suggest ideas / products / services / music / shows to improve your life

– It will filter out all advertising / marketing unless you opt-in

– So that’s the end of advertising, marketing, influencers

– It will be your therapist, dietician, coach, friend, advisor, consigliere, teacher and mentor

– Hackers will develop open source models that will be good enough for many daily activities, run locally, or in a trusted environment (eg Wikipedia)

– They won’t be as capable as the massive models, eg OpenAI / Microsoft, but will be good enough for many tasks

What if AI doesn’t get massively smarter?

– AI only gets marginally smarter and more capable

– Probability – 5%

– AI does not get smarter or more capable

– Probability – 5%

American Hypocrisy over Tariffs

by | May 16, 2024 | capitalism, ChatGPT, geopolitics, US, US politics

Me: I want to talk about the logic behind tariffs. The Biden administration just introduced a whole bunch of new tariffs on products coming out of China and that seems to be in direct opposition to the idea of free trade and open markets. How does the US justify tariffs? What’s the logical framework they use?

ChatGPT:

The US justifies tariffs on several grounds, even though they contradict the principles of free trade and open markets. Here’s the logic they use:

1. Protecting Domestic Industries: Tariffs can shield nascent or struggling domestic industries from foreign competition. By making imported goods more expensive, domestic products become more competitive in the local market, supporting local businesses and jobs.

2. National Security: Some industries are critical for national security. The US argues that relying on foreign countries, especially potential adversaries, for essential goods like steel, semiconductors, or pharmaceuticals can be risky. Tariffs on these imports can incentivize domestic production.

3. Trade Deficits: Tariffs can be a tool to address trade imbalances. The US has a significant trade deficit with China. By imposing tariffs, the government aims to reduce this deficit by making Chinese goods more expensive and thus less attractive, encouraging consumers to buy domestically produced items.

4. Retaliation and Negotiation: Tariffs can be used as a bargaining chip in trade negotiations. The US might impose tariffs to retaliate against unfair trade practices or to pressure other countries into changing their policies. It’s a form of economic leverage.

5. Revenue Generation: Tariffs also generate revenue for the government. Although this is less significant today compared to historical reliance on tariffs for funding government operations, it’s still a factor.

6. Economic Strategy and Industrial Policy: Tariffs can be part of a broader strategy to encourage specific sectors. For example, tariffs on certain tech products might be aimed at boosting the US tech industry’s competitiveness on the global stage.

In essence, while tariffs oppose the concept of free trade, they’re justified as a tool for protecting domestic interests, ensuring national security, correcting trade imbalances, leveraging negotiations, and driving strategic economic policies. Critics argue, however, that these measures can backfire, leading to higher prices for consumers, trade wars, and economic inefficiencies.

Me: But aren’t these the same basic arguments countries have always made for imposing tariffs and duties on foreign products? And aren’t they same arguments the US has tried to prevent other countries for using via the World Bank and IMF? 

ChatGPT:

Absolutely, these arguments have been around for centuries and are indeed the same ones the US and other countries have historically used to justify protectionist measures. The irony is palpable, especially considering the US has been a vocal proponent of free trade through institutions like the World Bank and the IMF. These institutions often encourage or even pressure developing countries to lower tariffs and open up their markets, promoting the benefits of free trade.

Here’s the nuanced breakdown of this irony:

  1. Historical Consistency: The US, like many other countries, has long used tariffs to protect its industries, especially during its early industrialization period. The arguments for protecting nascent industries and securing national interests are timeless and have been part of economic policies for centuries.
  2. World Bank and IMF Policies: The World Bank and IMF, heavily influenced by the US and other developed nations, have promoted policies of economic liberalization and deregulation in developing countries. These policies often come with the rationale that open markets lead to greater efficiency, economic growth, and integration into the global economy.
  3. Selective Application: The US has often applied different standards domestically versus internationally. Domestically, it might impose tariffs to protect specific industries or address strategic concerns. Internationally, it promotes free trade, arguing that it leads to overall global economic growth and stability.
  4. Strategic Interests: When pushing for lower tariffs abroad, the US and its allies argue that open markets benefit everyone in the long run by creating more competition, lowering prices, and fostering innovation. However, when it comes to its strategic interests, the US is quick to revert to protectionism, showing a dual approach based on context and interests.
  5. Realpolitik in Trade: International trade policies are often driven more by realpolitik than by ideological consistency. Countries, including the US, tailor their trade policies to their strategic economic and political interests, even if it means appearing hypocritical.

In summary, while the arguments for tariffs have remained consistent over time, the selective application of free trade principles versus protectionist measures highlights the pragmatic and often self-serving nature of international trade policies. The US, like many other countries, uses whatever tools and arguments are most advantageous for its current economic and strategic needs, even if it means contradicting its own advocacy for free trade.

American Hypocrisy Over China

by | May 9, 2024 | capitalism, climate change, Politics, propaganda, Propaganda Watch, Public Relations, US politics

I’m not an expert on world trade disputes, but it seems to be that the U.S.A.’s current whining about Chinese manufacturing is pathetic and hypocritical. American manufacturers, with the full support of the U.S. Government, has spent 40 years outsourcing their manufacturing to China in order to benefit from lower Chinese wages and TCO, so they could sell their cheap products to the world. Those same policies that benefited U.S. companies in the past now pose an economic threat, as Chinese companies make and sell their own goods to the world. There’s a stunning level of hypocrisy criticising China while having benefited from these manufacturing dynamics, but try to find that perspective articulated in the mainstream U.S. media. Instead they just continue to act as the P.R. arm of the U.S. government and its corporate owners.

And surely we want the world for have as much cheap, high quality green energy products as possible, don’t we? On one hand, the U.S. government says that climate change is a top global priority – on the other hand, they don’t want China to produce too many products to solve the problem.

Me:

The U.S. government is complaining that China is “creating an oversupply of clean energy products”. They are also complaining that China is “overproducing” products and “dumping” them on global markets. This seems churlish to me. I thought the US believed in “open markets” and capitalism? Don’t the US also use tariffs and government funding to make their manufacturers more competitive?

ChatGPT:

You’re picking up on the contradictions that often emerge in international trade rhetoric. The U.S. has long championed open markets and free trade, but that support is sometimes tempered by national interests and the desire to protect domestic industries.

Let’s break down the criticisms you’re mentioning:

     

      1. Oversupply of Clean Energy Products: China has heavily invested in clean energy manufacturing, like solar panels and batteries. The oversupply issue is essentially that China can produce more than the global market demands. This drives down prices, benefiting consumers and countries looking to transition to renewable energy but also putting pressure on non-Chinese manufacturers who struggle to compete with lower-priced imports.

      1. Dumping Allegations: Dumping refers to selling products abroad at prices below their normal value (often below production costs) to capture market share. Critics in the U.S. argue that China’s subsidies and state support lead to artificially low prices that damage U.S. manufacturers.

      1. U.S. Use of Tariffs and Subsidies: Yes, the U.S. has its own protectionist policies, such as tariffs and subsidies. The Inflation Reduction Act of 2022, for instance, incentivizes U.S. clean energy manufacturing, while tariffs imposed during the Trump administration continue to impact trade with China.

    In essence, while the U.S. preaches free markets, it’s not above using government interventions to protect its industries. The complaints about China are often rooted in the notion of maintaining a “level playing field,” where countries are expected to follow a similar set of market rules. However, these rules are often defined through political and economic lenses that favor the rule-maker’s interests.

    These dynamics reflect broader tensions in global trade, where the line between fair competition and protectionism becomes blurry, especially with strategic sectors like clean energy.

    Me:

    Can you give me examples of where the US used its economic and military power to make sure its manufacturers didn’t have to worry about a “level playing field”?

    ChatGPT:

    The U.S. has often wielded its economic and military power to protect and advance its manufacturers’ interests, sometimes at the expense of the concept of a “level playing field.” Here are a few notable examples:

       

        1. Marshall Plan (1948-1952): After World War II, the U.S. implemented the Marshall Plan to aid Western European reconstruction. While it provided crucial support for European economies, it also tied many of the aid recipients to American products and markets. The plan ensured European countries remained aligned with U.S. interests and created a favorable trading environment for American manufacturers.

        1. Operation Ajax (1953): The CIA-backed coup in Iran removed Prime Minister Mohammad Mossadegh and reinstated the Shah. The overthrow protected U.S. oil interests and their control over Iran’s oil resources, ensuring that American and British oil companies retained profitable operations in the region.

        1. Intervention in Latin America: Throughout the 20th century, the U.S. supported coups and regimes in Latin America to ensure stability favorable to American businesses. In Guatemala (1954), the U.S. supported a coup to protect United Fruit Company’s interests after land reform threatened its dominance.

        1. Trade Agreements and WTO Disputes: The U.S. has leveraged its negotiating power in international trade agreements like NAFTA and the WTO to secure preferential treatment for its manufacturers. At the same time, it has challenged other countries at the WTO for practices that disadvantage U.S. companies, winning cases like the one against China for rare earth export restrictions.

        1. Tariffs on Japanese Electronics and Cars (1980s): As Japan became a significant competitor to the U.S. in cars and electronics, the U.S. used tariffs and quotas to restrict Japanese imports and protect its own manufacturers.

        1. Recent Trade Wars with China: The U.S. imposed tariffs on a wide array of Chinese goods to counter what it claimed was unfair competition due to Chinese government subsidies, currency manipulation, and intellectual property theft. The tariffs effectively protected certain U.S. industries, even as they strained global supply chains.

      These actions demonstrate how the U.S. has historically prioritized its national and economic interests, often invoking the language of free markets but frequently resorting to state intervention, military action, or diplomatic leverage to secure advantages for its industries.