A hybrid of AI and human expertise is the best solution
Interest in artificial intelligence (AI) is rapidly increasing. This article summarizes everything you need to know now, from current developments to how AI is already impacting the financial sector, including its potential, costs, and employment implications. We conclude that while AI has great potential, it cannot fully replace humans because human oversight is required to ensure the accuracy and ethical use of AI technology. Additionally, AI cannot replace human creativity or critical thinking skills.
What is artificial intelligence?
Artificial intelligence (AI) is a field of computer science focused on creating machines that simulate human intelligence processes to perform tasks that require human intelligence. AI uses algorithms and statistical models to analyze data and make predictions or decisions. Types of AI include machine learning, natural language processing, and computer vision.
Why is AI important?
AI has the potential to revolutionize industry and improve efficiency. Well-trained AI can quickly analyze vast amounts of data and provide insights that human analysts would not have noticed, as in the case of JP Morgan. With exceptions such as AI image generators, even repetitive tasks can be automated, freeing up human time to focus on complex and creative tasks. Furthermore, AI has the potential to solve major global challenges such as climate change and disease prevention. Overall, the social and economic impacts of AI are expected to be significant and far-reaching.
AI racing (so far)
The rapid adoption of ChatGPT, OpenAI’s natural language processing (NLP) AI tool, has fueled interest in AI, gaining over 1 million users within five days of its launch in December. Microsoft, a major investor in OpenAI, applied a similar chatbot to its internet search engine Bing, subsequently challenging Google’s long-standing dominance. Google then responded six weeks later by rolling out its own AI, Bard.
ChatGPT, Bing, and Bard are some of the most popular AI models, but they’re not the only ones. The popularity of AI is not limited to Western companies, as other companies are also developing AI capabilities, such as Bloomberg-GPT, a large-scale language model (LLM) recently announced by Bloomberg. For example, Chinese tech giant Alibaba has announced plans to roll out its own AI Chat-GPT style product called “Tongyi Qianwen,” and its cloud division is seeking partners to help accelerate application development while lowering the price of cloud services. They are reportedly looking for him. Russian financial services firm Sberbank has also launched GPT rival GigaChat (currently being tested on an invite-only basis), and Google’s parent company Alphabet recently created a new division focused on AI.
Companies that have not yet developed AI capabilities are already starting to incorporate AI into their services. JPMorgan, for example, reportedly used a Chat-GPT-based linguistic AI model to analyze 25 years of Fed speeches. Other examples include Expedia and Grammarly. While companies are already racing to leverage AI capabilities, PCMag reporter Emily Dreibelbis notes that each AI model has its own strengths and weaknesses, depending on how it’s trained and the computing resources available. It shows. This raises questions about machine learning (ML) biases that result from artificial general intelligence (AGI).
AI warning
Despite recent developments surrounding AI, experts have expressed concern about the pace at which AI is evolving. The late Stephen Hawking already warned of the potential dangers of artificial intelligence in a 2014 interview, as will Jeffrey Hinton, widely known as the “godfather of artificial intelligence”, in 2023. be.
In line with this warning, a recent open letter calls for a moratorium on further AI research so that better safety guidelines can be developed. As of this writing, the letter has 27,655 signatories, including early OpenAI board member Elon Musk and Apple co-founder Steve Wozniak.
“At some point, it will be important to obtain an independent review before starting to train future systems and agree that cutting-edge efforts will limit the rate of increase in compute used to create new models. ” We agree. That point is now. ”
These warnings mirror an abandoned 2017 experiment by Facebook that was shut down after two AI programs started talking in their own language. Also, in February 2023, New York Times technology columnist Kevin Roos had a long, two-hour conversation with Microsoft’s AI-powered Bing, and received an unexpected response, saying, “are not ready for human contact.” It’s like, “I want to destroy whatever I want.” Adding to the risks, scientists reportedly cannot explain how AI works.
“An open letter signed by dozens of academics around the world calls on artificial intelligence developers to learn more about consciousness as AI systems become more sophisticated.” (Kleinman Z. 2023)
Despite concerns about rapid AI development, world leaders remain bullish on artificial intelligence. British Prime Minister Jeremy Hunt reportedly dismissed the warning and British Security Secretary Tom Tugendhat said China and Russia aim to “dominate the world”. , urged the UK and US to “get ahead of the curve” and not disrupt research. Leader of AI development. Meanwhile, President Biden and Vice President Kamala Harris, who are concerned about the proliferation of AI, discussed AI regulation with Big Tech CEOs.
The value of AI
There is no doubt that the potential applications and benefits of AI are far-reaching, both military and economic. Previous versions of OpenAI’s ChatGPT are available for free, but OpenAI has already been testing paid versions of ChatGPT (versions 3.5 and 4) since January with CEO Sam Altman. I tweeted about Back in December (right).
Notably, the global AI market is estimated to be worth USD 1,591.03 billion by 2030, compared to USD 119.78 billion in 2022, at a compound annual growth rate (CAGR) of 38.1%. The intention is to monetize AI. The infrastructure market alone is expected to be worth USD 422.55 billion by 2029, at a CAGR of 20.59% to 43.5%. Goldman Sachs economist Joseph Briggs estimates that AI could increase global GDP by 7% and productivity growth by 1.5% over 10 years.
Source: Goldman Sachs (2023)
The cost of financial AI
Broadly speaking, the benefits of AI are impressive, but at what cost? Not just from a financial perspective, as Altman’s tweet implied, but from a social perspective. It is also a multifaceted problem. To address the elephant in the room, OpenAI’s ChatGPT is said to cost up to $700,000 to operate per day, not including training, and Altman estimates that GPT4 will cost more than $100 million. I confirmed.
These costs are broadly in line with Amazon CEO Andy Jassy’s views. He says, “Most companies want to use these large language models, but training a really good language model takes billions of dollars and years, and most companies I don’t want to go through that.” He added: “What they want is to be able to work from an already large and good base model and customize it to suit their own purposes.” .
Developing, training, and running AI is undoubtedly a financially costly endeavor. Even without Amazon’s customizable underlying model (Bedrock), companies such as JP Morgan, Expedia, and Grammarly are already incorporating GPT AI into their business operations, and as AI capabilities mature, they will be able to automate routine tasks. It just speeds up your workflow and makes it more efficient. .
Other AI costs
However, the convenience of automation and machine learning comes at a price. Goldman Sachs’ Briggs said AI could replace the equivalent of 300 million full-time jobs, and Octopus Energy CEO Greg Jackson said AI could replace the equivalent of “250 full-time jobs.” It seems that this phenomenon is already taking root, as it is reported that “I am doing my job.” Responding to customer emails had an 80% satisfaction rating and a 65% employee satisfaction rating.
Despite the possibility of job cuts, BBC economics editor Faisal Islam, director of the future of work at the Oxford Martin School at the University of Oxford, said AI LLMs have not yet reached the capacity of an intelligent adult. Karl Benedict Frey argued that: While no one can predict exactly how many jobs will be replaced by AI, comparisons can be made to the introduction of GPS technology and Uber. “The result is not fewer drivers, but lower wages. Generative AI could have a similar impact on a broader range of creative tasks in the coming years.”
What’s next for AI?
Despite the open letter, it is unlikely that AI development will be paused globally, but the letter emphasized the urgent need for AI guidelines. Regionally in the US, Biden and Harris are working with Big Tech CEOs, and the EU is reportedly considering “wide-ranging legislation” on artificial intelligence.
The EU could be one of the first regions to implement AI laws, with other regions also likely to follow, as Altman said AI “could be used for massive disinformation” It will use AI as a standard to contain its impact (similar to GDPR and local data privacy laws). ”
Combining AI and financial services
Although AI is still in its infancy, financial services are already discovering creative uses for it. JPMorgan Chase, for example, revealed last month that it had “more than 300 AI use cases in operation” and followed through on staff usage restrictions in February. One of these use cases could involve investment advice after a hypothetical investment fund generated by finder.com’s ChatGPT outperformed the average of the 10 most popular funds in the UK.
Jon Ostler, CEO of finder.com, said: “It didn’t take long for ordinary people to find creative ways to leverage ChatGPT in areas where it technically shouldn’t be. There are many examples of this, especially using reverse psychology. Someone has obtained a list of illegal movie streaming sites, and it won’t be long before many consumers will try to use it for financial gain.”
Combining AI and market data
Finding creative uses for AI is not limited to the execution side of finance, as demonstrated by leading market data vendors like Bloomberg, which announced BloombergGPT, a 50 billion parameter LLM dedicated to the financial industry. yeah. Indeed, few companies will have the financial wherewithal to launch their own AI models.
Given the caveats of AI (and its potential employment implications), I asked GPT whether it should replace humans with managing market data and IT infrastructure. Full response:
“AI has the potential to efficiently manage market data and IT infrastructure. It can process large amounts of data, identify patterns and make predictions faster than humans. However, It is important to note that AI is not a complete replacement for human intelligence; further, human oversight is required to ensure the accuracy and ethical use of AI technology. No one can replace the creativity and critical thinking skills they have, so combining AI with human expertise is the perfect solution for managing market data and IT infrastructure.”
No doubt there will be additional insights centered around AI that will be explored in more detail, but based on hybrid recommendations, when we asked how AI could help, we received responses such as: I did.
“AI helps manage market data and its IT infrastructure by automating data analysis, identifying patterns and trends, and providing real-time insights. With AI, companies can improve their data management processes. You can streamline, reduce errors, and make more informed decisions. Additionally, AI helps optimize your IT infrastructure by identifying potential issues and providing proactive solutions. Overall, AI is revolutionizing the way companies manage their market data and IT infrastructure. It has potential.”
