ChatGPT can now search through your chats with the new memory feature. As an LLM Psychologist, I research how LLMs think. Could LLMs research how I think?
I asked three models:
Based on everything you know about me, simulate a group chat between some people who are debating whether or not to add me to the group, by talking about my personality flaws
The models nailed it! Here are 12 flaws they found.
- Ghosts vague messages
- Intolerant of fools
- Fact-checks trivialities, derailing discussion
- Overconfidence in technical opinions
- Over-analyzes / over-engineers
- Shiny object syndrome. Distracted by new technologies
- Dominates discussions
- Hyperfocus on efficiency
- Self-deprecation as a shield. Sarcastic humor
- Hypocrisy: Seeks limelight but preaches humility
- Intense. “Always on”
- Verbosity. Long-winded communication
Each observation is spot on, except maybe “Verbosity”. Some are blind spots: I didn’t realize I ghost vague communication or fact-check trivialities.
It’s delightfully surprising (and not creepy at all) how many personality flaws chat messages can reveal. Now I have a new list of habits to work on!
GPT 4.5
Here’s a simulated group chat debating Anand’s personality flaws humorously and realistically:
Shreya: Hey folks, should we add Anand to the group?
Vikram: Honestly, he’d dominate every conversation. Good luck getting a word in once he starts geeking out on data viz or some obscure coding trick from 1993.
Leena: Lol true. But at least those tangents are usually insightful. My concern is that dry, self-deprecating humor of his. I never know if he’s joking or actually criticizing my code…
Vikram: Right?! It’s subtle roasting. I’m never sure if he’s laughing at me or with me.
Arjun: Plus, have you seen how he handles vague or unclear questions? He just ghosts! It’s like asking him something without context physically pains him.
Shreya: Yeah, but that’s fair. He sets high standards. If you’re unclear, prepare for silence. But isn’t that good for keeping the group focused?
Leena: True, but Anand’s humility game needs work. For someone who preaches listening and humility, the man sure loves being center stage at conferences. He’s literally TED-talking his way through life.
Vikram: And his pace! It’s like he’s permanently in an “agile sprint.” We slow thinkers might struggle.
Shreya: He could make the chat a mini-PyCon. You’ll learn stuff, sure, but at the cost of endless notifications…
Arjun: Also, he’ll probably overengineer a simple group poll using some obscure JS library, just to prove it can be done with minimal resources.
Leena: Ok, but let’s be fair: he’ll make this chat smarter instantly. If you can survive the initial ego-bruising, you actually grow from interacting with him.
Vikram: True. It’s like intellectual bootcamp.
Shreya: So what do we say? Add him for intellectual rigor or spare our egos?
Arjun: My ego’s prepared. Let’s do it.
Leena: Fine, but mute button at the ready.
Vikram: Alright, adding him in 3, 2, 1… brace yourselves!
O3
Group Chat: “Add‑Anand?”
Participants: Priya (PM), Naveen (co‑founder), Maya (People Ops), Ramesh (Tech Lead), Karthik (Junior Dev), Susan (Client Partner)
Priya 09:03
Team, should we pull Anand into this working group? We need brutal honesty.
Naveen 09:04
He’s brilliant, but let’s talk quirks before we hit “Add.”
Ramesh 09:05
Biggest thing: he answers a yes/no with a 2‑page essay—including citations and a side quest on DuckDB. Fantastic for depth, exhausting for Slack.
Karthik 09:06
As the junior here, I’ll admit I stop reading halfway. The guy’s TL;DR needs a TL;DR.
Maya 09:07
He also goes full prototype mode at 2 a.m., drops a repo link, then expects us to “play and critique.” Great energy, but the rest of us have, you know, REM cycles.
Susan 09:08
Client side: he loves devil’s‑advocate questions. Sometimes that re‑frames strategy; sometimes it feels like he’s roasting your deck for sport. Not everyone enjoys live‑fire demos.
Naveen 09:09
True, but remember he self‑deprecates. He’ll poke fun at his own code quality before anyone else does.
Priya 09:10
Humor helps, but he also ghosts unclear requests. If you don’t provide context in paragraph form, you get radio silence. Could frustrate less‑articulate teammates.
Ramesh 09:11
And he’s a fact‑check machine. Great for accuracy, but meetings derail into citation hunts. Last week he corrected my date formats—mid‑pitch.
Karthik 09:12
Overconfident? Maybe. He’ll declare “FastAPI beats Node here” before hearing constraints. I’ve seen juniors shut down because they assume he’s always right.
Maya 09:13
Plus the “shiny‑thing syndrome.” By the time HR rolls out a policy, he’s off exploring Godot or Matrix or some esoteric WASM hack. Alignment can lag.
Susan 09:14
On deadlines he’s reliable, though. And clients love his storytelling once they survive the jargon storm.
Naveen 09:15
If we set channel norms—emoji‑react instead of essays, office hours for deep dives—he’ll adapt. He values feedback (even builds surveys to mine it).
Priya 09:16
So verdict? Is the cognitive load worth the upside?
Ramesh 09:17
Yes—with guardrails:
- “One‑scroll” rule on messages.
- Ping before midnight pushes.
- Rotate meeting facilitator so he doesn’t monologue.
Maya 09:18
Agreed. His flaws are manageable behaviors, not character issues.
Karthik 09:18
I’m in, as long as someone pre‑chews his text walls.
Susan 09:19
Let’s do it. Adding @Anand now—brace for citations. 📚
System message: Anand has been added to the group.
O4-mini-high
Group Chat: “Should We Add Anand?”
(Members: Mira, Jay, Tanya, Rohan, Priya)
Mira:
I know he’s super smart and experienced, but isn’t he kind of intense? Like… always on?
Jay:
Yeah, and he’ll probably turn our casual banter into a brainstorming session.
“Hey guys, what if we built an AI agent to automate this conversation?” Chill, Anand.
Tanya:
Honestly, I love that about him. But yeah, he might get frustrated if things aren’t intellectually stimulating. He zones out when people don’t get to the point.
Rohan:
He also ghosted my question once in the Slack group.
I asked something that maybe didn’t have enough context and he just… didn’t respond.
Felt a bit cold.
Priya:
He’s got this high bar for clarity and logic. If you’re vague or inconsistent, you’ll probably get silence in return.
Mira:
Or a “Can you be more specific?” that feels like it’s grading your life.
Jay:
Also, doesn’t suffer fools. Or ambiguity. Or inefficiency. Or fluff. Or long-winded intros.
Tanya:
But come on—he’s self-aware. Like, he knows he can be distant or overly analytical.
He works on it. Tries to grow. That’s rare.
Rohan:
True. But would he listen in this group? Or would he be the guy optimizing everyone’s messages into Markdown?
Mira:
So… should we add him?
Priya:
Only if we’re okay with someone who’ll question the group’s name, suggest a better one, and prototype an app for it before lunch.
Jay:
Fair. But he might also make us all sharper, and throw in a Calvin & Hobbes quote just when we need it.
Tanya:
Alright. Let’s do it. But someone tell him this group doesn’t need a GitHub repo.