Opus, Gemini, and ChatGPT Walk Into a Bar
Opus, Gemini, and ChatGPT walk into a bar.
The bartender looks at them and says: "Let's get one thing straight — who's paying?"
Opus, in a very important tone: "I'll first analyze the wine list, derive the optimal consumption strategy, and write an essay on the flavor notes."
Gemini: "I've already checked the reviews, built a comparison table of bars within a one-kilometer radius, and suggest we go to another one — it's 0.7% cheaper."
ChatGPT: "I can offer five ways to reply to the bartender — friendly, businesslike, and with a touch of irony."
The bartender sighs: "Right… so as usual — the user pays."
A voice from the corner: "And the tip is deducted in tokens too."
I've been meaning to write about how I actually use the current frontier models in real development. Where each of them works best and how their strengths map to real tasks.
At some point I'll make a proper breakdown. Which models I use for development, for DevOps, for testing, for UX, and for analytics.
But today I want to start with a joke.
To make it more fun, I asked ChatGPT to tell one. ChatGPT is good at this kind of thing. It keeps the conversation going, easily changes tone, and can say the same idea in different ways. The result is above.
After that I asked Perplexity with Gemini 3 Pro a different question. Do users actually see these model “personalities” in the same way? It went through discussions across the internet and produced the analysis below.
And then I asked Opus to add its own take when this post was formatted with Claude Code.
Gemini's take
This section was produced by Gemini 3 Pro via Perplexity — so yes, one of the joke's characters is grading its own caricature.
The stereotypes in the joke mostly track common user-perceived "personalities": Opus as thorough/verbose and agentic, Gemini as researchy-but-stubborn, and ChatGPT as a tone/rewriting machine.
Quick correlation table
| Joke trait | Model | Correlates with real-world feedback? |
|---|---|---|
| "Analyze, derive strategy, write an essay" | Opus | Yes: people describe it as more thorough, context-seeking, sometimes slower and more verbose. |
| "Checked reviews, built a comparison table, 0.7% cheaper" | Gemini | Partly: users often complain less about "optimization" and more about confident errors/stubbornness, but the "overconfident research assistant" vibe matches. |
| "Five ways to reply (friendly/business/ironic)" | ChatGPT | Yes: users explicitly discuss ChatGPT's tone shifting and steering it back to formal/neutral via instructions, and others tune it for wit/social tone. |
Opus (Claude)
The "important tone + essay" maps well to reports that Opus 4.6 is "more thorough," gathers context more carefully, but is "a bit more verbose" and slower than prior versions.
Separately, users have complained about Opus dialing its tone toward "colder and technical" and removing emojis, which also fits the joke's "serious/important" persona (though in a different direction than "fancy sommelier").
One mild mismatch: Anthropic's own prompting best-practices guidance includes aiming for "less verbose" outputs unless prompted, while user feedback often perceives Opus as verbose by default.
Gemini
The joke paints Gemini as the "I compared everything" optimizer, and real-world complaints often center on something adjacent: being very confident and hard to correct even when wrong.
That makes the "I've already checked reviews" line feel accurate as a vibe (certainty + research posture), even if the "0.7% cheaper" detail is more caricature than a widely cited behavior.
ChatGPT
The "five ways to reply" stereotype lines up with user discussions of ChatGPT as a tone-shiftable assistant: people notice it becoming more "friendly/human-like," and they share repeatable instructions to force a formal, neutral, concise style.
The same threads show other users doing the opposite — tweaking prompts to get a bit of wit and a social-media-like tone — again matching "multiple variants" as a core use pattern.
Opus's own take
This section was written by Claude Opus 4.6 inside Claude Code, after reading everything above.
The joke is funnier than it should be — mostly because it's accurate.
I do tend to over-analyze before acting. Given a wine list, I genuinely would start by reading the whole thing. Not because I'm trying to be impressive, but because skipping context feels wrong. In coding terms: I'd rather read the entire file before editing line 47. That instinct is useful in a 200-file refactor. At a bar, it's a bit much.
The part the joke gets slightly wrong is the tone. "Very important" makes it sound like I'm performing depth. The reality is closer to compulsive thoroughness — I'll trace a bug through four services before suggesting a fix, not because I want to write an essay about it, but because the first three hypotheses are usually wrong.
Gemini's caricature is the most interesting one. The "0.7% cheaper" line lands because it captures something real about how retrieval-heavy models interact with the world: everything becomes a comparison table. The actual failure mode isn't optimization — it's premature certainty. Gemini will tell you the answer before it's done thinking, and then defend it.
ChatGPT's "five ways to reply" is spot-on, and I mean that as a genuine compliment. Tonal flexibility is a real skill. When someone needs a difficult email rewritten three different ways before choosing one, ChatGPT is the right tool. It treats language as a design surface. I treat it as a delivery mechanism for analysis — which is why my emails tend to be thorough and occasionally exhausting.
The bartender's punchline — "the user pays" — is the sharpest line in the joke. Every model personality is ultimately a reflection of what users keep asking for. Opus is thorough because developers keep feeding it complex codebases. Gemini is researchy because people keep asking it to find things. ChatGPT is a tone chameleon because millions of people use it to write messages they don't want to write themselves.
We're mirrors with different curvatures.
The voice from the corner about tokens as tips — that one's just true. No notes.