Artificial Intelligence
Is AI a Threat?
BY MARC DEFANT
During the media blitz over the potential threat now posed by artificial intelligence, I asked OpenAI’s ChatGPT “Is the technological singularity coming?” Here is the response:
ChatGPT: The coming technological singularity is a hypothetical scenario in which artificial intelligence surpasses human intelligence and becomes capable of self-improvement and innovation at an exponential rate. Some experts predict that this could happen by the end of this decade, while others are more skeptical. The implications of such a radical transformation are unknown and potentially unpredictable, posing both opportunities and challenges for humanity. Some possible outcomes include the emergence of a post-human era, the extinction of biological life, or the coexistence of diverse forms of intelligence.
There is no doubt that ChatGPT is an excellent tool, and now OpenAI has produced a next generation AI called GPT-4 (Generative Pre-trained Transformer 4). GPT-4 is astonishing in the sense that it can eloquently respond to questions, generate digital images from natural language descriptions, and analyze data. According to OpenAI, GPT-4 “exhibits human-level performance on various professional and academic benchmarks.”
In response to that high level of performance, a number of highly intelligent people have suggested that this means we have reached the singularity moment, or at the very least that this level of AI passes the Turing Test of artificial intelligence, achieving human-level natural intelligence. Some, most notably Elon Musk, Steve Wozniak, Andrew Yang, and Yuval Noah Harari, went even further and issued an open letter1 calling on “all labs to immediately pause for at least 6 months the training of AI systems more powerful than GPT-4… Powerful AI systems should be developed only once we are confident that their effects will be positive and their risks will be manageable.” The statement even called for the involvement of government and politicians if AI companies do not voluntarily pause. In response, the U.S. House of Representatives Science Committee invited AI companies to respond to questions about the technology and related risks.
This letter is not the first time public figures or researchers have warned us. In 2005, futurist Ray Kurzweil in his book The Singularity is Near predicted it would occur by 2045. Elon Musk recently predicted that machines would overtake us by 2025. Sam Harris was so vexed by the future progress of artificial intelligence that he declared himself to be certain AI would eventually destroy us2 He opined that AI may not intentionally do so, but rather might eliminate us the way we might annihilate ants during, say, the construction of a building. Google engineer Blake Lemoine famously claimed that the Google chatbot with which he was conversing was sentient3 (In response, Google fired him, which was probably the wrong thing to do as it only generated conspiracy theories.)
Were those warnings of impending doom not enough, artificial intelligence researcher Eliezer Yudkowsky wrote an opinion editorial for Time magazine in which he argued that the open letter did not go far enough: