Multimodal vs Text-Only AI Models: Which Helps Visualize Thinking Processes Better?
Text-only AI models are better for visualizing your thinking - and I say that knowing it sounds backward.
Ideas on thinking with AI, cognitive partnership, and building alone together.
Browse by Topic
Text-only AI models are better for visualizing your thinking - and I say that knowing it sounds backward.
--
In 2022, a single eight-word phrase changed how researchers understood AI reasoning.
Are you using AI to get answers, or to stress-test whether your answers are actually right?
Are you wondering whether AI can actually help you think in systems, or whether it just hands you diagrams and definitions you could find in any textbook?
Are you trying to understand which AI approach actually works better for learning - the kind that adapts through feedback loops, or the kind that talks back?
I ran the same proof-of-concept through both models last week.
Seventy-three percent of knowledge workers using AI report that they default to a single model for every cognitive task - the equivalent of using a hammer to both frame a wall and do finish carpentry.
A friend of mine - a senior software architect - called me last month half-frustrated, half-delighted.
The war game had been running for six hours.
Most people are using AI wrong - and the reason is embarrassingly simple.
The model gave me a plan. Bullet points, clean logic, reasonable steps. I read it twice and felt that familiar flatness - the sense that something important was missing, that the output was technically correct and strategically useless. So I changed the prompt. Not the task. The framing. I told the
A few months ago I watched a senior engineer kill a good idea.
Researchers at Google Brain found something strange in 2022: adding the phrase "Let's think step by step" to a prompt improved GPT-3's performance on grade-school math problems by over 40 percentage points.
A few months ago, a product manager named Dmitri came to me frustrated.
You're standing in a grocery store, paralyzed between two nearly identical yogurts.
Most people asking this question are looking for a reading list.
Fewer than 12% of knowledge workers can correctly name the type of reasoning their AI assistant uses when it makes a mistake - yet that distinction determines whether you catch the error or act on it.
My student typed the same question into ChatGPT seventeen times.
A client of mine - senior engineer at a logistics firm - spent three months building a GPT-4 pipeline to flag regulatory exceptions in shipping manifests.
You're about to accept a job offer. The salary is good, the role is exciting, and the deadline is tomorrow. Your gut says yes. Your spreadsheet says maybe. And somewhere between the two, you know you're probably missing something you can't quite name.
You're three hours into a problem you can't solve.
And that's exactly when most people stop. Right at the moment of friction. The question gets hard, the answer feels uncertain, and the instinct is to move on. But Socrates stayed. He pushed. He asked the next question, and the one after that, until the person he was talking to realized they had been
**Claude Opus 4 wins this comparison for enterprise thinking workflows that require , creative responses - and it's not particularly close.**
Picture this: you've fed a model the entire codebase, three months of Slack history, and a 400-page technical spec.
And that's the moment most people get it wrong.
A product manager I know - sharp, experienced, genuinely good at her job - spent three weeks trying to redesign her team's onboarding process.
Last year I lost three hours to a document I was supposed to finish in forty minutes.
Knowing about a cognitive bias does not protect you from it.
Most people using AI to think better are training themselves to think less.
You've already tried once. Maybe you opened a blank mind-mapping tool, stared at the center node, typed something like "my career goals," and then watched yourself produce a tidy hierarchy that looked organized but felt completely wrong - like a floor plan for a house you'd never actually live in. T
A product manager I know - Sasha, at a mid-sized SaaS company - had a candidate in front of her who looked perfect on paper.
Most people use AI to confirm what they already think.
Are you trying to think through a decision and finding that every AI response just agrees with you?
Are you staring at ChatGPT wondering why your answers keep coming back shallow, vague, or just slightly wrong?
Most people using AI to "think faster" are making themselves slower.
Most people assume AI systems are either confident or broken.
You're already doing it wrong. Not in some catastrophic way - just inefficiently. You're reading this sentence the way humans have always read things: sequentially, emotionally loaded, filtered through every distraction in your peripheral vision and background anxiety. An AI would have extracted the
Most people using AI in 2025 are running a calculator that occasionally writes poetry.
Everyone keeps using the word "understands" when they mean something else entirely.
My friend sent me a screenshot last week. He'd asked an AI to help him write a resignation letter, and the AI had done it - beautifully, warmly, in his voice - better than he would have written it himself. He stared at it for ten minutes and then didn't send it. He couldn't explain why. The letter w
Are you more excited about AI than you probably should be - or more afraid than the evidence actually supports?
--
The idea arrived at 11:47 PM. I had been stuck on a problem for six days - a structural question about a project that kept collapsing in the middle, like a bridge with no center support. I typed it into a chat window, not expecting much. The AI didn't solve it. Instead, it reflected the problem back
In 2022, a study published in *Nature* found that radiologists working alongside AI diagnostic systems had a 11.5% lower error rate than either the AI alone or the radiologist alone - but only when the radiologist was allowed to override the AI's recommendation.
--
A client - a product manager at a mid-size SaaS company - told me she'd been using Claude for six months and felt like she was "going in circles." Same prompts.
A client of mine - a product manager at a mid-size SaaS company - told me she'd stopped using AI tools almost entirely after one bad week.
Most productivity advice about AI gets the relationship backwards.
A client of mine - a product manager at a mid-sized SaaS company - came to me frustrated.
You're scrolling at 11pm. You weren't anxious an hour ago. Now you're certain the economy is collapsing, that a specific political figure is dangerous, that your career is stagnating compared to everyone else's. You didn't read a book. You didn't talk to anyone. You watched a feed that someone - som
A 2023 Harvard Business School field experiment - Fabrizio Dell'Acqua and colleagues embedding AI tools inside a Boston Consulting Group cohort - found that consultants using AI performed substantially better on tasks within AI's capabilities, then performed significantly *worse* on tasks outside th
Are you using AI to think - or letting it think instead of you?
Are you spending more time learning AI tools than actually finishing work?
A client of mine - a senior product manager at a mid-sized logistics company - told me last spring that she'd stopped exploring AI for her core operations.
Most people are using AI wrong - and the problem isn't the tool, it's the thinking behind the tool.
A product manager named Lena came to me frustrated about six months ago.
Sixty-three percent of knowledge workers who report feeling "replaced" by AI are doing one specific thing wrong - they're measuring the wrong thing entirely.
Most people are asking the wrong question about AI.
Are you getting advice from AI that sounds right for everyone and useful for no one?
Most people will not be replaced by AI. They'll be replaced by people who stopped clinging to how things used to work - people who noticed, early enough, that their mental models had quietly become fiction.
Json
The question I keep coming back to isn't whether AI is smart.
Most people using AI for data organization are solving the wrong problem.
Most people who try to use AI for thinking end up with a smarter-sounding version of the same thinking they already had.
**Large language models are the wrong tool for adaptive thinking - and we've been reaching for them anyway.**
The engineer's phone is dying. Forty percent battery. She's on a train somewhere between Vienna and Salzburg, running inference through an API call against a deadline, watching the latency timer climb. The model is thinking. Actually thinking - not autocompleting, but reasoning through a multi-step
A 2018 Harvard Business Review study by Michael Porter and Nitin Nohria tracked 27 CEOs across a combined 60,000 hours and found that genuine strategic thinking - the kind that shapes competitive position rather than just the next quarter - accounted for less than 21% of their working week.
Most people using AI as a philosopher are wasting the prompt.
You're staring at a decision you've been circling for three weeks.
A 2024 study from MIT's Computational Cognition Lab found that users who prompted AI with a single framing accepted the AI's first response as authoritative 78% of the time - even when the AI was demonstrably wrong.
Are you trying to figure out which type of AI actually *thinks through* a problem rather than retrieves a plausible answer?
Seventy-three percent of new AI users report abandoning their first tool within two weeks.
--
You've heard the hype. You've probably tried o1 or o3 once or twice and thought - wait, is this thing actually *thinking*? And now you're wondering whether you should restructure how you use AI for anything that actually matters intellectually.
Are you staring at a difficult algorithm, wondering whether to reach for a reasoning model or just use whatever chat interface you already have open?
You paste a math problem into ChatGPT. Wrong answer. You paste the same problem but add "Let's think step by step." Correct answer. That small phrase - four words - changed everything. That moment, experienced by millions of developers and researchers between 2022 and 2023, launched an entire sub-di
Most people are using AI wrong for hard problems - and they know it.
Most people are prompting reasoning models the same way they prompt autocomplete systems.
My screen is blank at 11pm. Deadline tomorrow. The usual tricks - walks, coffee, calling a friend - have already been exhausted. Then I type one sentence into an AI: *"What would someone with the opposite of my assumptions think about this problem?"* Within three minutes I have seven directions I ha
The most dangerous assumption in the age of AI is that the machine is smarter than you.
The model gets the wrong answer. You try again with the same question. Wrong again. Then you add six words - *"let's think through this step by step"* - and suddenly it's correct. Not kind of correct. Precisely, verifiably correct. Same model. Same question. Different prompt.
When researchers at Princeton tested GPT-4 on the Game of 24 - a math puzzle where you combine four numbers using basic arithmetic to reach 24 - the model solved it correctly about 4% of the time using standard prompting.
Most people use AI to avoid thinking. The ones getting sharper are using it to think harder - and the gap between those two groups is widening faster than anyone is publicly acknowledging.
A few months ago, a friend showed me his AI conversation history.
Neuroscientist Karl Friston has spent decades arguing that the brain is not a passive observer but a prediction machine - one that constantly generates hypotheses about the world and updates them based on incoming evidence.
Are you using AI the same way everyone else is - as a faster search engine or a writing shortcut?
You've probably wondered whether there's a smarter way to make decisions - not just in theory, but today, before lunch.
A colleague of mine - sharp guy, works in product strategy - spent three weeks convinced that his company should pivot to a subscription model.
Every time you feel impressed, unsettled, or betrayed by something an AI wrote, you are not responding to the AI.
My calendar blocked an hour for "deep work." I spent forty minutes deciding which deep work to do.
A colleague of mine - a sharp, skeptical engineer who prides himself on sourcing everything - told me last year that he'd started to feel differently about remote work.
Most people are using AI wrong. They feed it tasks and expect outputs. What they get is a faster version of themselves - same blind spots, same assumptions, compressed into seconds. The real appears when you do something counterintuitive: you expose the AI to experiences, not just prompts. You bring
A hospital administrator in Toronto told me she spent two years evaluating AI diagnostic tools.
Are you wondering whether the people debating AI's cognitive architecture actually need to include historians, nurses, or philosophers - or whether that's just performative inclusion?
Process-thinking will make you worse at working with AI.
Picture a philosopher in 1950, staring at Alan Turing's paper "Computing Machinery and Intelligence," deciding within three minutes that machines could never truly think - and closing the journal.
The 50% rule is a polite fiction we tell ourselves to feel in control.
AI doesn't make you dumb. Trusting it without questioning does.
Here's the claim most AI productivity writers won't make: using AI without deliberate constraints doesn't augment your thinking.
Deploying AI without mapping its risks in parallel isn't bold strategy.
A client of mine - a senior product manager at a fintech company - told me she spent three hours arguing with an AI assistant about a market analysis.
Have you ever finished a conversation with an AI and felt vaguely cheated - like you asked for something important and got back something technically correct but somehow hollow?
95% of people use AI for tasks. The real value is in thinking with it. Here's the difference, and why it changes everything.