Can Startups Save the World from AI?

Will on

February 3, 2023

I asked ChatGPT: Please write me 1000 words on what kinds of companies will be needed to help retrain and empower knowledge workers whose jobs will be reduced or eliminated due to advances in generative AI like ChatGPT.

ChatGPT’s verbatim answer [**with my not-too-snarky commentary inserted in brackets**]:

The increasing use of generative AI, such as ChatGPT, has the potential to greatly impact the workforce and job market. [**That’s the understatement of the year! But the impact can be positive as well as negative**]. With AI systems capable of automating many tasks previously performed by humans, there will likely be a need for retraining and empowering knowledge workers whose jobs may be reduced or eliminated.

To address this challenge, a variety of companies will be needed to provide services that support the retraining and empowerment of knowledge workers. Here are a few of the types of companies that will likely play a role in this process:

1. Professional development and training companies: These companies will offer training programs and courses designed to help workers acquire new skills and competencies that are in high demand in the post-AI job market. These training programs will focus on skills that are difficult for AI to replicate, such as creativity, empathy, critical thinking, and problem-solving. [**That’s a good list of training opportunities. Additional areas are in learning tools to couple physical presence/trust/assurance with AI and teaching the ability and confidence to act beyond the AI’s processing of digital information. Google’s Lamda is gearing up on the empathy side – there may be competition there, but interacting with empathy is likely a front-line human skill for quite some time.**]

2. Career transition companies: These companies will provide guidance and support to workers who have been displaced from their jobs due to AI. They will offer services such as resume building, interview preparation, and job search assistance. They will also provide career counseling to help individuals find new paths and opportunities in the job market. [**Hmm… I think ChatGPT has already been shown to be good at resume building and interview prep – I would not invest here. I asked for a list of careers that would be AI-safe – ChatGPT gave good advice. So I’d skip investing in counseling. AI already helps with job matching.**]

3. Upskilling and reskilling platforms: These companies will offer online learning platforms that allow workers to acquire new skills at their own pace. These platforms will provide access to a wide range of courses and resources, including tutorials, videos, and interactive simulations. They will also offer certification programs that help workers demonstrate their newfound skills to potential employers. [**Agree with this one. There are good investment opportunities, especially when the upskilling/reskilling is developed affordably using AI and teaches continuously-AI-enhanced rather than displaced skills. And certification will need to change to ensure there is no AI-based cheating in the process.**]

4. AI-powered job matching services: These companies will use AI algorithms to match workers with job opportunities based on their skills, experience, and preferences. They will help workers find new opportunities in industries and fields that are experiencing growth, even as others are being impacted by AI. [**Old news – everyone in this biz is already using some form of AI and they will rapidly adopt the latest generative tech as it becomes available. Not a lot of white space for startups.**]

5. Human-AI collaboration companies: These companies will focus on developing AI systems that can work alongside humans, rather than replacing them. They will help organizations find ways to integrate AI and humans in ways that complement each other and increase overall productivity. [**Big opportunity here with clear white space to invest in. A few startups and even scaled services like Amazon Mechanical Turk have been scaling human-AI collaboration for many years, predominately around tagging. The next frontier is to move upstream to higher cognitive load areas beyond tagging, such as prompt engineering, fact/source checking, and physical/digital world partnering. Across many industries, the upside will come from amplifying Subject Matter Experts with AI, and also training more people to be SMEs.**]

In addition to these types of companies, there will likely be a need for public-private partnerships and government initiatives that provide financial support for retraining and reskilling programs. This will help ensure that workers have access to the resources they need to succeed in the post-AI job market. [**A nice policy suggestion that some countries will likely embrace and some will not. America was sadly deficient in retraining / upskilling manufacturing workers as those jobs were outsourced/offshored. Hope we learn our lesson and get ahead of the game with AI.**]

In conclusion, as the use of generative AI continues to grow, it will be important to address the impact it may have on the workforce. [**It may have? How about “will certainly and quickly”.**] Companies that provide professional development, career transition, upskilling, job matching, and human-AI collaboration services will play a critical role in retraining and empowering knowledge workers whose jobs may be reduced or eliminated due to AI. These companies will help ensure that workers are equipped with the skills they need to succeed in the post-AI job market and continue to make valuable contributions to society.

My [Will’s] take: As you’ve read from too many places already, generative AI is the most profound advance in technological impact on society since the introduction of the iPhone in 2007. I’d argue that in a fairly small number of years, generative AI will have as much if not more impact on society than the introduction of the Mosaic Browser, thirty years ago this year. As technologists, operators, and investors, my partners and I could not be more excited to be a part of this sea change. 

This will be the eighth sea change that I’ve participated in as an entrepreneur, corporate exec, and/or investor: microcomputers (1975), IBM PCs (1981), Windows 3.0 (1990), Browsers (1993), Google (1997), Smartphones->iPhones (2001-7), scaled cloud via Amazon Web Services (2006), and now generative AI (2022). Yea, there were other things that mattered too (Mac fans, flame on; scale could not have happened w/o mobile, etc.), but I see those eight as the biggest step functions in computing tech impacting humanity at scale over the past ~50 years.

We are in the process of screening our entire portfolio (~50 companies held directly across 3 funds) to be AI+, AI?, or AI-. And I name the middle as a “?” because I think nothing is neutral to AI, it just may not yet be clear whether the company is more likely to come out on top or be negatively impacted by the advances. We are also looking at every new opportunity through a generative AI lens, first to make our own assessment, and then to see if the founders are looking far enough down the road to know how to create value through AI rather than being road kill by those who do it better.

The good news for us and our investors is that the vast majority of the sectors we’ve been investing in for many years, including Jobtech (AI++), Fintech (already employing AI), Healthtech (AI++), Agtech (AI+), Edtech (AI+) and of recent, and Climate (AI?, but we believe AI+) have produced companies that will clearly benefit from the rapid advances in generative AI. We are already hatching plans to support rapid transformation in our companies best poised to benefit from this sea change, starting this month. Here are three companies that can apply the next gen of generative AI in short order:

  • Masai School, India’s leading “zero-to-one” coding school is already embracing AI tech for coding assistance and has moved to verbal interviews to ensure grads can code independently of AI.
  • ZoomAgri is using advanced AI to quickly grade commodity grain transactions in Brazil, ensuring growers and buyers get fair prices.
  • Shipper can apply AI to their logistics platform in Indonesia to offer more efficient and cost-effective one-stop logistics solutions.

In the meantime, the Global South remains on a faster growth trajectory than the Global North. I predicted this in 2018, and I stand by it. All of our companies in the South and the 4 billion consumers they serve in the rising middle class will soon benefit from the innovation we are funding. The startups we fund will use AI to literally save jobs and save lives while making piles of money.

Will