If you thought they could lie fast before, now AI has been harnessed to spew them harder & faster


A new paper is out: A Critical Reassessment of the Anthropogenic CO₂-Global Warming Hypothesis: Empirical Evidence Contradicts IPCC Models and Solar Forcing Assumptions.

A Critical Reassessment of the Anthropogenic CO₂-Global Warming Hypothesis: Empirical Evidence Contradicts IPCC Models and Solar Forcing Assumptions
• Grok 3 beta
, • Jonathan Cohler
, • David Legates
, • Franklin Soon
, • Willie Soon

Let us examine the authors.

• Grok 3 beta: the first author is AI software, Elon Musk’s pet AI, to be specific. It is competent at stringing words together, but can you trust it?

• Jonathan Cohler: He’s a professional clarinetist with no scientific training (he has written software), but he’s also a vocal climate change denialist. Ironically, he’s also the author of The Puppeteers of Perception: How AI systems are designed to mislead. I guess now he has changed his mind and decided that AI is a path to the truth.

• David Legates: He actually has climatology credentials! But he’s been using them to deny climate change. He’s a creature of the Heartland Institute, and was recently appointed by Trump to a position at NOAA.

• Franklin Soon: He’s a high school kid. He’ll have to grow up a bit before we can kick him around.

• Willie Soon: A notorious climate crank. He’s an aerospace engineer affiliated with the Heartland Institute and a whole slew of far right think tanks. He has received hundreds of thousands of dollars, possibly many millions, from the fossil fuel industry, but he works damn hard to lie about his ties. He’s generally an awful person, worst of the bunch on that paper. He’s apparently also corrupted a teenaged boy to follow his path in lunacy.

I am unperturbed by the human authors on this atrocity, who have been babbling like this for decades, but am very concerned about the use of AI to churn out garbage. The paper is dense and technical, and mostly impenetrable by me (dammit, Jim, I’m a biologist!), but clearly goes against the climate consensus, denying any role of carbon in global climate change. I’m going to reject its conclusions out of hand because a) it flouts all the information delivered by real, human, scientists who are experts in the field, b) it’s a machine-generated Frankensteinian mishmash cobbled together from cherry-picked sources; c) it was fed by a team of kook climate deniers who fed it garbage in, and got garbage out, designed to mislead. But you know all the climate change deniers are going to be citing this thing without question.

What I dread, though, is when even more denialists pick up on this. You want to argue against vaccines, or a spherical earth, or evolution, or racial equality, it’s easy: crank up Elon’s Lie-Making Machine, feed it trash from any of a number of delusional web sites, and it’ll spit up a technically dense, grammatically competent, flaming heap of bullshit that you can cite in your debates. I imagine the Discovery Institute and AiG and Jay Bhattacharya’s corrupted NIH already have some dumbass intern gearing up to crank out more papers with a shiny pseudoscientific gloss. The Gish Gallop will be mechanized.

Comments

  1. says

    Well, Artificial Intelligence and a bunch of lying idiots have automated throwing shit against the wall. They have may have made it faster than a Gish Gallop. But, their horse is dead.

  2. monad says

    At least so far it’s only in a journal obviously dedicated to motivated reasoning. Here’s hoping ones that actually want to be at all trustworthy will take the warning. :(

  3. Robbo says

    i’d actually like to see a crappy paper about flat earth! would be entertaining.

  4. John Morales says

    Not all AIs are chatbots; this paper was not written by AI, but without the AI it would have been too laborious to do:
    https://www.nature.com/articles/s41558-025-02276-3

    Article — Open access
    Published: 07 March 2025
    Worldwide rooftop photovoltaic electricity generation may mitigate global warming
    Zhixin Zhang, Zhen Qian, Min Chen, Rui Zhu, Fan Zhang, Teng Zhong, Jian Lin, Liang Ning, Wei Xie, Felix Creutzig, Wenjun Tang, Laibao Liu, Jiachuan Yang, Ye Pu, Wenjia Cai, Yingxia Pu, Deer Liu, Hui Yang, Hongjun Su, Mingyue Lu, Fei Li, Xufeng Cui, Zhiwei Xie, Tianyu Sheng, …Jinyue Yan Show authors
    Nature Climate Change volume 15, pages 393–402 (2025)
    Abstract
    Rooftop photovoltaic (RPV) is often understood as a niche contribution to climate change mitigation. However, the global potential of RPVs to mitigate global warming is unknown. Here we map the global rooftop area at 1-km resolution, quantifying 286,393 km2 of rooftops worldwide through geospatial data mining and artificial intelligence techniques. Using nine advanced Earth system models from the coupled model intercomparison project phase 6, we reveal that RPVs could substantially contribute to reducing global temperatures by 0.05–0.13 °C before 2050. Region-specific analysis underscores the variability in RPV potential and the necessity of tailored approaches to optimize RPV deployment, considering local solar resources, existing infrastructure and grid carbon intensity. Our findings reveal that leveraging RPV systems offers a viable and impactful strategy for reducing carbon footprints and combating climate change globally, while advocating targeted interventions to enhance the benefits of RPVs, particularly in areas with high solar radiation or rapid urbanization.

    (the section on methods details the process used for determining extant world-wide rooftop area)

  5. Hoosier Bluegill says

    Maybe we can crank up an AI chatbot to debunk these “papers” as fast as they come out.

Leave a Reply