Critically Thinking about Artificial Intelligence: the good, the BAD, and the ugly...
Part 2: The Bad
This is the second of my four-part series about Artificial Intelligence (AI). See Part 1 [the Good], Part 3 [the Ugly] and Part 4 [Takeaways]. [Note: these are being written entirely by a human, not AI!]
As in Part 1, I utilized ChatGPT as it is the most representative of present-day AI options available to the public. I asked it a current technical (science-related) question I already knew the answer to — and then critiqued the response given.
Question #2: Is wind energy a net societal benefit?
The AI Answer (verbatim):
Yes, wind energy is generally considered a net societal benefit for several reasons:
Renewable and Sustainable: Wind energy is a renewable energy source that harnesses the power of wind to generate electricity. Unlike fossil fuels, wind is an abundant resource that does not deplete over time. By utilizing wind energy, we can reduce our reliance on non-renewable sources and contribute to a more sustainable energy future.
Climate Change Mitigation: Wind energy is a clean source of electricity that produces virtually no greenhouse gas emissions or air pollutants during operation. By replacing fossil fuel-based power generation with wind energy, we can significantly reduce carbon dioxide and other harmful emissions that contribute to climate change and air pollution. This helps mitigate the impacts of climate change and improve air quality, leading to public health benefits.
Energy Independence and Security: Wind energy diversifies the energy mix and reduces dependence on imported fossil fuels. By harnessing domestic wind resources, countries can enhance their energy independence and security, reducing vulnerability to fluctuations in fuel prices or geopolitical tensions associated with fossil fuel imports.
Economic Benefits: Wind energy projects create jobs throughout their life cycle, including manufacturing, installation, operation, and maintenance. These jobs span a range of sectors, from manufacturing and construction to engineering and project management. Additionally, wind energy investments can stimulate local economies, attract new industries, and generate tax revenue for communities.
Rural Development and Land Use: Wind farms often occupy rural areas, providing economic opportunities for landowners and communities. Wind energy projects can offer lease payments to landowners hosting turbines, providing a stable income source. They can also support local businesses, such as construction companies or maintenance services, and contribute to the economic development of rural regions.
Resource Diversification: Wind energy complements other renewable energy sources, such as solar power, hydropower, and geothermal energy. Combining different renewable sources in an integrated energy system helps ensure a reliable and resilient energy supply. Wind energy can be particularly advantageous in regions where solar resources are limited or in areas with high wind potential.
While wind energy does have some considerations, such as potential visual or noise impacts, proper project siting, and technological advancements can mitigate these concerns. Overall, the widespread adoption of wind energy offers numerous societal benefits, including environmental sustainability, climate change mitigation, economic growth, and energy independence.
…….
Oh dear, the AI answer is seriously wrong on several counts…
To begin with, it says: “wind energy is generally considered…”. I wasn’t asking for (and don’t care about) what people generally consider, but rather the facts. What people consider is instead a measure of how successful propaganda has been, not facts
Isn’t AI supposed to be fact-based? Then let’s see a comprehensive and objective list of facts. None of that was in the answer. Instead, I was given wind lobbyist talking points.
I asked about “NET societal benefits,” which means: a) identifying the pluses, b) spelling out the minuses, and then c) coming to a conclusion as to which dominates. None of that was done!
Let’s also briefly look at each of the six AI reasons given:
1 - AI says that wind energy is a net societal benefit because it is renewable. Just because something is renewable does not mean that it is a net societal benefit! For example, biomass has now been acknowledged to be a liability (e.g., here & here). Further, many of the key components of wind turbines (e.g., rare earth materials) are NOT renewable or sustainable. In other words, you can’t have a renewable and sustainable energy source if its components are not renewable and sustainable. None of that was mentioned.
2 - AI claims that wind energy can significantly reduce carbon dioxide and other harmful emissions. This is totally bogus. Wind energy produces WAY more CO2 than nuclear, and typically more CO2 than gas by itself! (See this Report for details.) The bottom line is that no genuine Scientific study has ever concluded that wind energy makes a consequential reduction of CO2. None.
3 - Diversity for the sake of diversity is foolishness. The only meaningful diversity here is if we are adding energy sources that are equal to or better than existing sources — which we are not! (BTW, the comparison would be on three [3] counts: economics, reliability, and environmental impact. Wind energy is inferior on all three.)
4 - The “creating jobs” argument has been thoroughly debunked (on multiple grounds) for years (e.g., here), yet AI is clueless. Industrial wind energy job claims are almost always wildly optimistic because there is no penalty for lying (e.g., see here).
5 - Yes there are some apparent winners but: a) it’s very doubtful that farmers really end up with a net benefit [e.g., see here.], and b) it is the economic benefit to the community that is important, not to a few individuals. [The net community financial impact (when thoroughly and objectively calculated) is almost always negative.]
6 - This is little more than #3 rephrased — maybe to see if I’m paying attention?
Every one of the AI “reasons” is either highly suspect or outright false. This AI answer is blatant lobbyists’ propaganda, rather than a reasoned comprehensive, and objective answer to my important question.
Even more telling is that in the six (6) AI “reasons,” there was not a single liability even mentioned! It wasn’t until the summary paragraph that AI finally admits to some wind energy liabilities. However: a) AI called these “considerations” and b) for each of the few liabilities they chose to mention, they immediately state that these problems can be mitigated (false). In other words, AI is blatantly attempting to downplay very serious wind energy shortcomings.
When discussing this with a friend, they asked a good question: is it possible that AI gave this answer as it simply was not aware of the numerous wind energy liabilities? To resolve that I asked AI: “Please list all possible wind energy liabilities.”
Here is the AI answer, which enumerated nine (9) possible downsides!
Three notes: 1) this list is not complete (e.g., it did not list military interference, which is well-documented), 2) as noted in the AI answer to my initial question here, AI again injected words trying to downplay the significance of some of these problems, and 3) several liabilities on the AI list did not appear in the AI answer to my question about whether wind energy is a net societal benefit.
I’d ask Why? for all three of these.
The fact that the AI answer to my important question was highly suspect or outright false, was NOT due to a lack of information, but rather an undeclared political bias. ChatGPT cherry-picked specific data, exaggerated that data to appear extremely positive, and ignored crucial information about downsides that are well-documented. What good are technical answers loaded with hidden political biases?
Such an AI answer is neither objective nor comprehensive.
The score I’m giving AI on Technical Question #2 is 0%.
PS — Please encourage other open-minded associates to sign up for this free substack. Also please post this on your social media. The more citizens that are educated on key issues like this, the better our chances of success…
Here are other materials by this scientist that you might find interesting:
Check out the Archives of this Critical Thinking substack.
WiseEnergy.org: discusses the Science (or lack thereof) behind our energy options.
C19Science.info: covers the lack of genuine Science behind our COVID-19 policies.
Election-Integrity.info: multiple major reports on the election integrity issue.
Media Balance Newsletter: a free, twice-a-month newsletter that covers what the mainstream media does not do, on issues from COVID to climate, elections to education, renewables to religion, etc. Here are the Newsletter’s 2023 Archives. Send me an email to get your free copy. When emailing me, please make sure to include your full name and the state where you live. (Of course, you can cancel the Media Balance Newsletter at any time - but why would you?
Thanks for reading Critically Thinking About Select Societal Issues! Please pass a link to this article on to other associates who might benefit. They can subscribe for FREE to receive new posts (typically about once a week).
Hi, John. As you might remember, I've been working in the field of AI for over 60 years. I was one of the originals. Fast forward 10 years and I worked with Dr. Carl Page, who was working on data analysis algorithms. We couldn't do much on computers to prove it, because back in the late 60s, early 70s, despite landing on the moon, there wasn't sufficient computing power and there weren't adequate data to search. Carl's sons were Carl, Jr and Larry ... Page. Now, down to ChatGPT.
This is clearly not an AI implementation. It is humans changing rules and loading static databases. That to me is not AI. There is a decision tree mechanism that is called AI today, and I guess I would go along with that, to some extent, though I implemented that approach in the 90s to control quality in manufacturing lines. I'm inclined to the idea that all that is AI today is due to computing power; the math and algorithms were available in the late 60s and early 70s. ( I worked on speech recognition in the early 70s. Again, a compute-constrained problem to be able to separate phonems when the speech ran together. Solved with more pattern comparison at human acceptable speeds.)
On ChatGPT, who's function I implemented back in the early 90s as part of that manufacturing application, I asked the question:
Provide a summary of the contents of the Phizer Papers released through FOIA request.
Response from ChatGPT: I apologize, but as an AI language model, my responses are generated based on pre-existing knowledge up until September 2021. As of my last update, I am not aware of any specific Pfizer Papers released through a Freedom of Information Act (FOIA) request related to COVID-19 vaccines. It's possible that new information has emerged since then.
Ummm. Ding, wrong answer ! I suppose I can work on asking the question (training me) until I get to the a level the program can understand. But, the facts and knowledge on the technology, the mandate effectivess, and the safety and effectiveness of the &psi.mRNA and LNP technology was available in 2020. Some papers go back 30 years! If the software was AI, it should not have been so superficial. In fact, it turns out the probably approaches 100% that the response given was manufactured by direction of the federal government and has no scientific basis at all. It's a plug-in triggered by certain words in aggregate. AI can be manipulated to give mal-information at the desire of controlling interests. This information can be embedded within information that "sounds authentic".
Perhaps a follow up would be to ask about other forms of energy and their uses. Would it mention the need for liquid fuels for transportation? Would it mention that the “to cheap to meter” comment was in reference to nuclear fusion?