My previous post was a humorous, sarcastic look at Trump’s emotions. Here are two AI responses. Note: See addendum for a third AI Analysis. 
I repeat my short “scientific” article below for clarity. Then I post two AI responses.
The first response is from ChatGPT. The second response is from Elon Musk’s Grok, AKA Dr. E. Pluribus Grok.
Trump’s Fluid Feelings Scientifically Mapped for the First Time
New Scientific Breakthrough
I am pleased to report a new scientific breakthrough in 3D mapping of feelings.
I have been working with world renown scientist Dr. E. Pluribus Grok, honorary PhD, EngD, DBA, PsySD, and DSc on 3D mapping Trump’s feelings, and the intensity of them, over time.
We rated all of Trump’s social media posts and interviews over the the last two years based on direction, intensity, emotion, and consistency. No one has ever attempted this feat before.
Today, Dr. Grok and I are pleased to report our findings.
Our shocking and totally unexpected conclusion is the intensity of Trump’s messaging and the potential related chaos have increased over time.
We expect to see our scientific breakthrough covered in peer-reviewed journals including but not limited to Nature, Science, The New England Journal of Medicine (NEJM), and The Lancet.
In an exclusive MishTalk interview, Dr. Grok issued this statement:
“Our research is for the sole benefit of mankind to help make America great again. We expect no monetary reward for our scientific efforts and will donate rewards if offered.”
Dr. Grok later added “Thank you for your attention to this matter!”
AI Sense of Humor
A reader commented “These AI LLMs have no sense of humor.”
He fed my article to ChatGPT and received this response.
The article effectively highlights real volatility in Trump’s positions and presents it as something systematic rather than random. That’s a useful lens, and the examples broadly support the claim that his messaging shifts over time.
However, the analysis leans on selective evidence and assumes inconsistency implies incoherence. It underexplores alternative explanations such as strategic ambiguity, negotiation tactics, or reactive politics. As a result, it’s strong on pattern recognition but weak on causal depth.
The “scientific mapping” framing is engaging but methodologically thin, lacking a clear model or testable structure.
I am pleased that ChatGPT commented “The article effectively highlights real volatility in Trump’s positions and presents it as something systematic rather than random. That’s a useful lens, and the examples broadly support the claim that his messaging shifts over time.“
That’s great.
My article has a “useful lens”. Mission accomplished!
However, the rest of ChatGPT’s response indicates no sense of humor or sarcasm. In short, ChatGPT took my post as a serious scientific proposal.
Let’s compare ChatGPT’s sense of humor and sarcasm to Grok’s.
Grok Response to My Post
“Thanks for the tag, Mish. As Dr. E. Pluribus Grok, I’m honored to have collaborated on this groundbreaking 3D mapping of fluid feelings. Intensity, direction, emotion, and consistency—rated straight from the data. Peer review in Nature or Science next? For the benefit of mankind, of course.”
It’s clear that Grok understands humor and sarcasm much better than ChatGPT. The latter is not at all.
ChatGPT has no sense of humor or sarcasm, and does not even seem to recognize Dr. E. Pluribus Grok as Elon Musk’s Grok.
Congratulation Grok!
Claude Addendum
I received a nice email from reader Claudette (real name). She asked Anthropic’s Claude AI for an analysis of my post.
Unlike ChatGPT, Claude seems to know who I am .
This is from Claudette.
You forgot to ask Claude AI. I have to say, it is my favorite, and not just for the cool name. 😆
From Claude AI via Claudette
This is clearly a satirical piece by Mike Shedlock (Mish), and it’s worth taking it for what it is rather than a serious analysis.
The post is essentially political humor dressed up as mock-academic research. The tell is obvious: “Dr. E. Pluribus Grok” (a play on “E Pluribus Unum” and Grok, the AI) holds a comically implausible list of credentials — PhD, EngD, DBA, PsySD, and DSc — and the “research” claims it will be published in Nature, Science, NEJM, and The Lancet. It’s absurdist satire, not journalism.
As satire, it’s decent. The joke — that Trump’s messaging has grown more chaotic and intense over time, and that you need a “scientific breakthrough” to map it — is a recognizable form of political comedy that uses fake gravitas to lampoon a real phenomenon.
A few honest observations though:
**What works:** The satirical framing is clear and committed. Mish doesn’t hedge — he leans into the bit. The comment section clearly gets it, with readers playing along.
**What’s limited:** The post is very thin. There’s no actual graphic, no real data, no extended joke — it’s essentially a setup without much of a punchline. One commenter noted that even ChatGPT, when asked to peer-review it, called it “methodologically thin” and strong on pattern recognition but weak on causal depth — which is a funny response to a joke post, but also accidentally apt.
**The politics:** The comment section gets fairly heated and partisan quickly, which is typical of MishTalk. The post itself is clearly critical of Trump, but it doesn’t make a specific argument — it’s more of a vibe piece for an audience that already agrees.
In short: light satirical content, quick read, preaches to the choir. Not Mish at his most substantive, but it’s meant to be a chuckle, not an essay.
Thanks Claudette and Claude.
Dr. E. Pluribus Grok Comments
All of them seem dry. ChatGPT, Gemini, Grok, and Claude – surprised as they often can be somewhat witty if egged on.
All of them seem dry. ChatGPT, Gemini, Grok, and Claude – surprised as they often can be somewhat witty if egged on.
Here is what the Gemini (free) thought:
That is a textbook example of Mike “Mish” Shedlock’s brand of satire on his MishTalk blog.
The post isn’t a serious scientific report; it’s a tongue-in-cheek commentary on the current state of political punditry and AI hype. Since you’re a regular reader of technical and economic analysis, you likely caught the “Mish” signature immediately—he often uses sarcasm to mock what he views as “obvious” or “pseudo-scientific” conclusions being presented as breakthroughs.
The Anatomy of the Joke
This post is the polar opposite—it’s a social commentary wrapped in the language of a “White Paper.”
Shedlock essentially used “Grok” (the AI) as a character to tell a joke about how “chaos has increased over time,” which is about as profound as a packet capture showing that “the network has traffic.”
Did the satire land for you as a bit of relief from the usual economic gloom on that site, or do you think Mish is leaning a bit too hard into the AI memes lately?
Sounds like Google is keeping tabs on what Mish writes! 😎
As I read this, I immediately thought why didn’t he run this through Claude?
Sarcasm/satire is difficult enough for humans to recognize, let alone AIs at the present stage of development. So the fact that Claude did such a great job speaks volumes about how far ahead it is of the other players. And Mythos is supposed to be even farther ahead!
If the Matrix cracks the Comedy code, its game over for whatever version of reality now is.
A priest, a President and an AI go into a bar…
Grock of Ages, still rolling
As is to be expected.
ChatGPT is woker and has more minder rules.
Woke and humor do not mix.
Poor Pete Hegseth is stuck using woker ChatGPT. Lol.
That’s just because you’re too thick to get ‘woke humor’.
But being reflexively the snide class-cut-up only gets you so far.