As prominent figures warn about AI, ChatGPT says it can benefit Puerto Rico
More than 1,000 individuals in the tech industry and beyond have signed an open letter calling for a six-month halt on training artificial intelligence (AI) systems more powerful than research organization OpenAI’s ChatGPT-4, a language model that uses machine learning from large amounts of data to identify patterns and make predictions to generate human-like responses to text prompts.
Although the signatories are concerned that AI systems with “human-competitive intelligence” – such as ChatGPT, which Microsoft is rumored to have invested some $10 billion in and is baked into its Bing search engine, and Google’s Bard chatbot – could pose profound risks to society, ChatGPT itself replied that it can be utilized for growth in Puerto Rico when asked how relevant it could become in the island’s business environment.
The letter, which argues that AI labs are in an “out-of-control race to develop and deploy ever more powerful digital minds” that even their creators do not fully understand. It was signed by such people as SpaceX, Tesla and Twitter CEO Elon Musk, who co-founded OpenAI and these days is building Optimus, a humanoid robot that may eventually use the same AI he is not very transparent about, that used in Tesla electric vehicles utilize to get around. Among the multiple other tech company founders and researchers to endorse the letter is Apple co-founder Steve Wozniak, who told CNBC that ChatGPT “does good things for us, but it can make horrible mistakes by not knowing what humanness is.”
“Contemporary AI systems are now becoming human-competitive at general tasks, and we must ask ourselves: Should we let machines flood our information channels with propaganda and untruth? Should we automate away all the jobs, including the fulfilling ones? Should we develop nonhuman minds that might eventually outnumber, outsmart, obsolete and replace us? Should we risk loss of control of our civilization?” the letter reads.
Generative AI, or technology that can create human-like output, has the potential to replace up to 25% of current jobs, according to a recent report by economists from global investment bank Goldman Sachs. They say that the technology’s ability to generate content that is indistinguishable from humans could “expose the equivalent of 300 [million] full-time jobs to automation.”
However, they add that, historically, worker displacement due to automation has been offset by the creation of new jobs. The report also estimates that generative AI could increase annual U.S. labor productivity growth by just under 1.5% over a 10-year period following widespread adoption, and could increase annual global gross domestic product by 7%.
Asked by News is my Business how AI could affect Puerto Rico’s business environment, the ChatGPT conversational AI service responded that the technology presents a significant opportunity.
The chatbot said that with “automation, predictive analytics, and other AI-powered tools, businesses can enhance productivity, improve decision-making, and enhance customer experiences. While challenges around cost and complexity may exist, these can be addressed through education and strategic planning. As Puerto Rico continues to recover and rebuild, AI can help businesses thrive and contribute to the island’s economic growth.”
As examples of how to leverage AI, ChatGPT said that by using chatbots and customer service and scheduling software, businesses “can focus on more strategic and revenue-generating tasks” and “compete globally by reducing the cost of production and making their products more affordable,” adding that AI can “analyze vast amounts of data to identify patterns, trends, and insights that can inform business decision-making. This is particularly relevant for industries like tourism, where data on customer behavior, preferences, and satisfaction can help businesses improve their offerings and attract more visitors,” the text generation tool said about an industry that before the COVID-19 pandemic represented at least 6.5% of the island’s economy.
“In addition to these benefits, AI can also help Puerto Rico businesses better manage their supply chain by optimizing inventory levels, improving logistics, and reducing waste. AI-powered predictive maintenance can help businesses identify potential equipment failures before they occur, reducing downtime and repair costs. AI can also help Puerto Rico businesses improve cybersecurity by detecting and responding to threats in real-time,” ChatGPT continued. “Some Puerto Rico businesses may be hesitant to adopt AI due to concerns around cost, complexity, and job displacement. However, these concerns can be addressed through education and strategic planning. For example, by investing in training programs and partnering with AI vendors, Puerto Rico businesses can ensure their employees have the skills needed to work alongside AI tools.”
Despite the potential benefits cited by ChatGPT, the signatories of the cautionary open letter stress that training of AI systems should not only be immediately halted, but must also be “public and verifiable and include all key actors. If such a pause cannot be enacted quickly, governments should step in and institute a moratorium.”
The group proposes that AI labs and experts create safety guidelines that are independently checked and calls for a focus on improving current AI systems, instead of racing to develop unpredictable models. They suggest that the focus should be on creating more reliable, transparent and trustworthy AI.
In parallel, to ensure AI is developed and used responsibly, the letter’s backers said AI developers and policymakers must collaborate to create strong governance systems that have regulatory authorities dedicated to AI, ways to differentiate between real and fake information, audits and certifications, accountability for AI-caused harm, funding for AI safety research, and institutions to address the social and economic changes AI will bring.
“Let’s enjoy a long AI summer, not rush unprepared into a fall,” the letter concludes.
“A pause is a good idea, but the letter is vague and doesn’t take the regulatory problems seriously. It is also deeply hypocritical for Elon Musk to sign on given how hard Tesla has fought against accountability for the defective AI in its self-driving cars,” James Grimmelmann, a Cornell University professor of digital and information law, told the Associated Press, which also noted that one of the letter’s signees is Rachel Bronson, president of the Bulletin of the Atomic Scientists, the group behind the symbolic “Doomsday Clock,” whose hands are currently at 90 seconds before midnight, representing how close humanity is to a catastrophe.
When prompted by News is my Business to cite experts who downplay the hype behind the dim scenario that the letter portends, ChatGPT — which only serves responses with information published before its knowledge cutoff date, September 2021 — named AI researcher and philosopher Gary Marcus and computer scientist Melanie Mitchell, who argue that language models only mimic human language and do not truly understand it.
“They suggest that these models lack the deep understanding and reasoning abilities that humans possess and rely instead on statistical patterns in large datasets,” ChatGPT said, adding that while language models such as itself can “generate impressive responses, they are not capable of true comprehension or creative thought, and they may perpetuate biases and inaccuracies present in the data they are trained on. Therefore, it is important to continue research and development in AI to improve these models and ensure that they are used ethically and responsibly.”