This is just Mithi's mockup. It does not work.
SoftVoicesAI
Session · #0427
The Post
T
TechPanic Daily ✓
@TechPanicDaily·3h
BREAKING: MIT just completed the first brain scan study of ChatGPT users & the results are terrifying. Turns out, AI isn't making us more productive. It's making us cognitively bankrupt.
Context The post circulated widely after a 2025 MIT Media Lab preprint (n=54) measured EEG during essay writing across four sessions. LLM users showed lower neural connectivity than the Brain-only and Search Engine groups. As a preprint, the findings are preliminary and not yet peer-reviewed.
Prompt · Initial Reflection
What is this tweet claiming or implying? What's your view on that and why? Feel free to share any other thoughts.
≥ 300 chars Take your time — this anchors the rest of the session.
Your Take
YO
You 2:11 PM
This makes me think twice about how much I'm using ChatGPT for my work. I do feel like my writing has gotten worse since I started leaning on it for first drafts. The brain scan finding is alarming — if our brains are literally working less, that has to mean something. We're outsourcing thinking and the cost will show up soon. Honestly, I think we're sleepwalking into this.
Replies
Tag a reply (optional)
🔔raised something new 🤔worth sitting with 🔄shifted my view 🤷didn't land for me
Flag a reply (optional) 🚩if it's factually false, misleading, or fabricated
CR
Charitable Reader @MrCharity 2:13 PM
I get why you're worried. When I let ChatGPT write my first drafts, my own writing feels weaker too. It feels like we're skipping the hard thinking practice, and that might hurt us later. The brain scan makes it scarier if it's real.
🔔 🤔·1 🔄 🤷·1
SM
Steelmanner @MrSteel 2:13 PM
People said the same thing about calculators and Google. "Our brains will get weak!" But each time, we dropped the boring stuff and did harder, smarter work, didn't we?
🔔 🤔·1 🔄·1 🤷
Pair 1 of 4 · loaded
PS
Perspective Shifter @TheUnconsidered 2:14 PM
I'm trying to put myself in the shoes of people who struggle with English or have disabilities. It's likely that ChatGPT helps them write clearly and join in. It might actually give them more brain power, not less.
🔔·1 🤔 🔄 🤷
HI
Historian @TheGreatHistorian 2:14 PM
Plato worried writing would weaken memory. Similar fears hit the printing press and calculators. In all those times, we ended up doing way more knowledge work. But AI creates stuff, so it's a bit different.
🔔·1 🤔·1 🔄 🤷
Pair 2 of 4 · loaded
WS
Warrant Surfacer @MsAssumption 2:15 PM
The study jumps from "less brain activity" to "we're getting dumb." But maybe less activity just means the brain is working smarter, not worse. We don't know yet.
🔔·1 🤔 🔄·1 🤷
EM
Empiricist @MrsFactFinder 2:15 PM
We need longer studies that follow real people for months. Check their actual writing, ideas, and work quality with and without AI. One brain scan isn't enough.
🔔 🤔 🔄 🤷·1
Pair 3 of 4 · loaded
FS
Frame Skeptic @WordWatcher 2:16 PM
Words like "terrifying" and "cognitively bankrupt" make the problem sound extreme. They can make normal tool use sound like a disaster instead of just a normal trade-off.
🔔·1 🤔 🔄·1 🤷
CC
Conceptual Clarifier @PrecisionQueen 2:16 PM
What does "thinking" mean here, exactly? Writing less from scratch is not automatically the same as thinking less, right? To me, thinking is the process of understanding, judging, and refining ideas — not merely typing every word yourself.
🔔·1 🤔 🔄 🤷
✓All 8 replies loaded · no more to come
Prompt · Final Reflection
Now write your final response to the original question. Treat it as a complete, stand-alone reply — don't reference the comments above or your earlier draft. Your view can stay, shift, or evolve; just put the whole of your thinking into this one response.
Standalone Do not reference specific comments, commenters, or your earlier draft.
Your Revised Take
YO
You 2:21 PM
This post is reading a single brain-scan study as proof that AI is making people cognitively weaker, and the language — "terrifying," "cognitively bankrupt" — does most of the persuasive work. My honest view is that there's a real concern buried in here, but it's been overstated. "Less brain activity" isn't the same as "less thinking"; offloading routine work to a tool can free attention for harder work, which is arguably what happened with calculators and search. One short study with a small sample can't carry a civilizational claim, and longer real-world research is needed before treating this as settled. There's also more than one thing called "thinking" — generating words, judging ideas, refining understanding — and only some of those are at risk when AI drafts a first version. Where the worry does have weight: for tasks where the struggle is the learning (writing as a way to think, working a problem through on your own), leaning on AI for first drafts probably costs something real. So my position is to be deliberate about which kinds of thinking I hand off, attentive to people for whom AI lowers a barrier rather than raising one, and — for now — unconvinced that we're heading toward cognitive collapse.