The generative AI boom will usher in an age of accelerated productivity and prosperity for some and profound disruption for others, McKinsey said.

• Whole swaths of business activity are set to become more embedded in software—with potential economic benefits of as much as $2.6 to $4.4 trillion annually.
• But it will also profoundly disrupt some professions. The firm estimated a few years ago that about half of worker hours worldwide were spent on tasks that could be automated. Now it’s raising the figure to as high as 60-70%.
• It’s happening fast. About 75% of the potential value from generative AI is expected to come in four business functions: customer operations, marketing and sales, software engineering, and R&D.

More Stats and Insights

Pew Research found 62% believe artificial intelligence will have a major impact on jobholders overall in the next 20 years, but only 28% think it will significantly affect them personally.

PwC found only 36% of respondents as a whole strongly or moderately agree that the skills needed to succeed in their job will change significantly over the next five years, and only 43% say they have a clear sense of how the skills required for their job will change at all over that span. 

25% of American jobs are highly susceptible to automation. Everyone will eventually be impacted. It won’t matter if you are in one of the Highest Paying Occupations, Fastest Growing Job Sectors, or one with the Most New Jobs. Some of the estimated 73 million or 46% of workers eliminated from automation by 2030 could switch to one of the projected 11.9 million new jobs. However, a potential reduction of 61.1 million workers from our Labor Force is still cause for serious concern.

Me, I am rethinking everything! So the first question I had for chatGPT:
“If our GDP is reliant on 68% of consumer spending, our Government’s federal income is reliant on 52% from Individual Income Taxes along with 30% from Payroll Taxes, how will we make up the massive shortfalls from automation job losses that could grossly add to our existing $31 trillion in national debt, or crater our economy despite trillions in cost savings for businesses?”

chatGPT 4.0 response: The scenario you’re describing poses a significant policy challenge, as automation has the potential to significantly disrupt job markets and, by extension, the tax base that governments rely on for revenue. If automation leads to widespread job losses, it could indeed lead to a shortfall in government revenue from individual income taxes and payroll taxes, which currently constitute a substantial portion of federal income in many countries.

Here are some strategies and policy options that governments might consider to address these challenges:

1. Reskilling and Workforce Development: By investing in education and training programs, governments can help workers transition from jobs that are at high risk of automation to those that are expected to be in higher demand. This might include promoting STEM education, as well as providing vocational training in sectors that are less susceptible to automation.
2. Tax Policy Reform:

• Value Added Tax (VAT) or Goods and Services Tax (GST): A consumption tax could offset some revenue losses, as it is based on spending rather than income. This could be less affected by automation-related unemployment.
• Automation Taxes: Governments could consider implementing taxes on businesses that benefit most from automation, though this approach is controversial as it could potentially slow down innovation.
• Progressive Taxation: Adjusting tax brackets to ensure that those with higher incomes pay more could also help compensate for revenue losses, assuming that high earners would continue to earn income even in a highly automated economy.

3. Universal Basic Income (UBI): Some policymakers and economists have proposed UBI as a solution to automation-driven job displacement. While it would require significant government expenditure, proponents argue that it would help maintain consumer spending levels and thus support the overall economy.

4. Adjusting Social Security and Payroll Taxes: The government could consider revising social security systems and payroll taxes to adapt to new employment patterns. This might involve new types of contributions for gig economy workers or those in flexible employment.

5. Promoting New Industries and Innovation: By investing in emerging industries and new technologies, governments can help create jobs and generate new sources of revenue.

6. Capital Gains and Wealth Taxes: If automation leads to increased corporate profits and concentration of wealth, governments could consider higher capital gains taxes or the introduction of wealth taxes to ensure that the benefits of automation contribute to public finances.

7. Corporate Tax Reform: Ensuring that corporations pay a fair share of taxes, possibly by closing loopholes that allow tax avoidance, and possibly by implementing minimum tax rates, could help address revenue shortfalls.

8. Government Bonds: In the short term, governments might issue bonds to cover deficits, but this approach would need to be managed carefully to avoid exacerbating national debt issues.

9. Public-Private Partnerships (PPPs): Leveraging private sector investment for public projects can also help stimulate economic growth and job creation without overburdening public finances.

10. Reducing Government Spending: This is a traditional fiscal response to reduce deficits, but it can be counterproductive in times of economic contraction and can further exacerbate unemployment.

11. Incentivizing Employment: Governments can provide incentives for businesses to keep human workers employed, even when automation might be more cost-effective in the short term.

12. Investing in Infrastructure: Government investment in infrastructure can create jobs in the short term and increase productivity in the long term.

Each of these approaches has its own set of challenges and trade-offs, and the most effective response would likely involve a combination of these strategies. Policymakers would need to carefully consider the potential impacts of automation on the economy and the job market, as well as the distributional effects of any policy changes. It would also require international cooperation, as automation and its economic effects are not limited by national borders.

The 1956 Dartmouth workshop was when AI gained its name and mission, and it is widely considered the birth of AI. Since then, AI has been evolving to provide superintelligence, hyperintelligence, or assisted intelligence. In the broader context, General AI is about robotics, digital twin technology, and automation used for productivity while rapidly improving time to insights by combining Big Data, Machine Learning, Reinforcement Learning, Foundational Models, and Large Language Models to solve problems that are too complex, complicated, and expensive to scale for humans.

Today, more than 1158 AI tools are deployed in the market, the AI market size is estimated at $119.78 billion. Over 203 U.S. Startups are also developing new AI tools and applications as almost every CEO discusses how they plan to use the technology as the next step in their digital transformation to capture the estimated $2.6 to $4.4 trillion of yearly economic value.

Generative Pre-trained Transformers, commonly known as GPT, are a family of neural network models that use the transformer architecture and are a key advancement in artificial intelligence (AI) powering generative AI applications such as ChatGPT.

GPT-4 large language model supports multimodal (images, text, sound, and video) that are the next step closer to general AI with some improved security controls. At a rumored 100T parameters, GPT-4 would be over 500 times larger than GPT-3.

Last week, more than 1,000 scientists and tech leaders, including Elon Musk, signed an open letter calling for a pause in the race to develop more powerful artificial intelligence models. The letter channeled a certain dread that many feel about this fast-changing technology. It also became a lightning rod for criticism from both AI advocates and skeptics.

John von Neumann, Vernor Vinge , and Ray Kurzweil argue that it is difficult or impossible for present-day humans to predict what human beings’ lives would be like in a post-singularity. The primary AI fears are hallucinations, bias, disinformation, and productivity improvements that result in job loss and loss of agency to a sentient technology. Based on the current level of transparency and global levels of cooperation, the idea that we can regulate technology seems unrealistic.

My simple AI truths
1. All technology can be used for good or evil.
2. AI will accelerate the rate of change along with our potential for promise and peril.
3. Those postulating fears from technology are typically heavily invested and have the most to lose.
4. AI won’t entirely replace humans, but humans with AI will replace humans without AI.

For a deeper dive …
Attention is All You Need from Google Research
Ring Attention with Blockwise Transformers for Near-Infinite Context from UC Berkeley
Research from OpenAI
Emerging Architectures for LLM Architecture
AI Index Report from Stanford University
AI Transparency Index from Stanford University
Holistic Evaluation of Language Models (HELM) from Stanford University
State of Generative AI in 7 Charts from CBInsights
Generative AI Startup Market Map from CBInsights

Biden Issues Executive Order on AI safety and security
National AI Advisory Committee

Pair programing was good, mob programming was better, I suspect Copilot powered by Codex, the new AI system created by OpenAI will be one of the many AI tools making developers lives better.