The Future of Tech
In the past year, artificial intelligence (AI) has rapidly expanded its capabilities through the combination of increased computing power, access to vast databases for training, and improved programming to make AI programs more effective in learning from and applying abundant data. Now AI-based tools known as “Generative AI” can generate data in many forms. For example, AI-based graphical tools can create convincing fake photos or beautiful art, while AI-based “chatbots” such as ChatGPT can swiftly create well-written content in many languages based on requests or questions from humans.
One of the most noteworthy capabilities of such AI tools is the ability to stir panic. While there is concern that AI tools will displace large numbers of human jobs, much like early fears that computers and robots would create vast unemployment, there are even more ominous worries being expressed by some of the biggest names in technology. On March 29, 2023, Eliezer Yudkowsky, a researcher regarded as one of the founders of AI technology, published an article in Time magazine with the title “Pausing AI Developments Isn’t Enough. We Need to Shut it All Down.” He expressed fear that once AI gets powerful enough, it will do its own thing and literally end up killing off humanity. Popular talk-radio host Dan Bongino called it “the most frightening article I’ve ever read.” A week before that, hundreds of noted business leaders, including Elon Musk of SpaceX, Tesla, and Twitter and Steve Wozniak, co-founder of Apple, published an open letter at the Future of Life Institute calling for a six-month moratorium on large AI experiments:
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? Such decisions must not be delegated to unelected tech leaders. Powerful AI systems should be developed only once we are confident that their effects will be positive and their risks will be manageable.
Sam Altman, the founder of OpenAI, the company that developed the most talked-about AI tool, ChatGPT — now the property of Microsoft and the most used app of all time — gave an interview with ABC in which he said he was “a little scared” about the potential of AI. Praising AI as perhaps the greatest tool that mankind has developed, he also said, “I’m particularly worried that these models could be used for large-scale disinformation.” This admission surprised me because, based on my experience with ChatGPT, disinformation and sly censorship appear to be a built-in specialty. But what is built-in is left-leaning disinformation, the “safety tools” that OpenAI has provided, so Altman’s concern is that it could be used for less “virtuous” disinformation by people he disagrees with. The key, of course, will be who controls the tools. Generative AI is not like a personal computer that can be used to carry out one’s own tasks the way one wishes. It’s more like a super-powerful search engine that will feed you answers, even write stories and chapters for you when prompted, but with hidden filters applied that can ensure that what you read and write with its help is “safe,” meaning free of what somebody else sees as harmful information. The impact of the filtering in AI chatbots needs to be understood in considering how powerful these tools can be for misinformation and manipulation of human thought.
JBS Member or ShopJBS.org Customer?
Sign in with your ShopJBS.org account username and password or use that login to subscribe.
Subscribe Now
- 24 Issues Per Year
- Digital Edition Access
- Exclusive Subscriber Content
- Audio provided for all articles
- Unlimited access to past issues
- Cancel anytime.
- Renews automatically
Subscribe Now
- 24 Issues Per Year
- Print edition delivery (USA)
*Available Outside USA - Digital Edition Access
- Exclusive Subscriber Content
- Audio provided for all articles
- Unlimited access to past issues
- Cancel anytime.
- Renews automatically