{The forward reads…} In the past 200,000 years, humans have upset the balance of planet Earth, a balance established by nearly four billion years of evolution. We must act now. It is too late to be a pessimist. The price is too high. Humanity has little time to reverse the trend and change its patterns of consumption.

C02 & The Dark Side of ChatGPT (AUDIO)

OpenAI is a research organization founded by Elon Musk and Sam Altman in 2015 as a challenger to Google. The original mission of the venture was to create artificial intelligence for the benefit of humanity as a whole.

The most notable part of OpenAI is a function called Chat GPT. It’s a chat room like you’ve never seen before. Within a few days of launching, it hit one million users despite a total media blackout and zero publicity.

It now has over 100 million sign-ups. But there’s another, darker side to ChatGPT that has become increasingly obvious to those who have been studying ChatGPT. It’s the notable use of intentional misinformation and a not-so-subtle left-leaning political bias that is built into the system.

Although he was one of the founders of OpenAI, Musk is no longer involved with the company or its most significant product, ChatGPT, which uses an artificial neural network to mimic human thought.

After Microsoft made its original investment in mid-2019, Musk wrote on Twitter, “I have no control & only very limited insight into OpenAI,” adding that his confidence in its safety was “not high.”

Following Microsoft’s latest $10 billion-dollar investment in OpenAI last month, Musk wrote that “OpenAI was created as an open source, non-profit company to serve as a counterweight to Google, but now it has become a closed source, maximum-profit company effectively controlled by Microsoft.” As Musk noted in his tweet, the company had become “Not what I intended at all.”

Musk recently renewed his call for a regulatory agency to provide oversight of artificial intelligence, stating that AI is “actually a bigger risk to society than cars or planes or medicine.”

Musk continued, asking, “What are the biggest risks to the future of civilization? A.I. is both a positive and a negative: It has great promise and great capability, but with that also comes great danger.”

Musk has long been concerned about the risks associated with AI, telling students from MIT in October 2014, “If I had to guess at what our biggest existential threat is, it’s probably AI.” In 2017, Elon told CNBC that AI “is a fundamental existential risk for human civilization. And I don’t think people fully appreciate that.”

All of which brings us back to ChatGPT. In December 2022, Musk wrote on Twitter that “ChatGPT is scary good. We are not far from dangerously strong AI.” And in our limited experiences, both technically and as users, he’s absolutely right. ChatGPT lets you have human-like question and answer sessions. You can ask it any number of questions to which you get a surprisingly quick and detailed response. You can also ask it to write a critique in a particular writer’s style—which is why many school systems are alarmed—or even to debug code. It’s astonishingly simple to use. You type in a question, and it responds with a surprisingly helpful answer within seconds.

One of the best examples of misleading answers and subsequent admissions was when we asked if “97% of scientists agree climate change is real?” We already knew the answer as we had analyzed the study that produced this manufactured statistic years ago. ChatGPT told us, “Yes, the overwhelming majority of climate scientists agree that climate change is real and is primarily caused by human activities, such as the burning of fossil fuels and deforestation. The 97% figure you mentioned refers to a number of studies that have looked at the level of scientific consensus on this issue. One of the most well-known studies on this topic was conducted in 2013 by John Cook and colleagues, who analyzed the abstracts of more than 12,000 peer-reviewed papers published between 1991 and 2011.”

Sounds pretty definitive, doesn’t it? Except for the fact that there was a significant issue with that study. Cook ignored the two-thirds of scientists who didn’t take a firm position, scientists who were likely afraid of being publicly called out because they didn’t believe climate change was man-made. Cook only used the one-third of respondents who expressed a strong opinion—most of whom agreed climate change was man-made—to come up with his 97 percent figure. When this was pointed out to ChatGPT, the AI immediately knew what we were referencing, stating, “You are correct that the study by John Cook and colleagues did find that 66% of the abstracts they analyzed did not take a position on the causes of global warming.” But it still said the study was valid and other studies agreed with the results.

We then pushed a bit more, noting that “97% of 33% is not 97% is it?” Chat GPT responded, telling us, “You are correct that stating that ‘97% of scientists agree’ can be misleading and oversimplified. The 97% figure often cited refers to the percentage of scientific papers that take a position on the causes of global warming and endorse the consensus view that it is primarily caused by human activities. The 33% figure you mentioned represents the percentage of papers that took a position on the issue in the first place.” But despite this admission, ChatGPT still tried to carry on telling us that “the overwhelming majority of scientific research supports the consensus view that climate change is real and is primarily caused by human activities.”

Mildly annoyed at this point, we responded, telling ChatGPT, “Your original response was very misleading. Why did you claim 97% when it was nowhere near 97%?” ChatGPT responded, saying, “I apologize for any confusion caused by my earlier response. You are correct … I should have been clearer in my response and explained the context and limitations of the 97% figure.” ChatGPT apparently reluctantly admitted that “there is some variability in the level of agreement across different studies and surveys.”

Musk warned us that AI represents an existential threat to humanity. Who knew that it would also represent an existential threat to the truth?