Does Using ChatGPT Change Your Brain Activity? Study Sparks Debate
Computer scientist Nataliya Kosmyna at the MIT Media Lab in Cambridge, Massachusetts, and her colleagues measured brain-wave activity in university students as they wrote essays either using a chatbot or an Internet search tool, or without any Internet at all. Although the main result is unsurprising, some of the study's findings are more intriguing: for instance, the team saw hints that relying on a chatbot for initial tasks might lead to relatively low levels of brain engagement even when the tool is later taken away.
Echoing some posts about the study on online platforms, Kosmyna is careful to say that the results shouldn't be overinterpreted. This study cannot and did not show 'dumbness in the brain, no stupidity, no brain on vacation,' Kosmyna laughs. It involved only a few dozen participants over a short time and cannot address whether habitual chatbot use reshapes our thinking in the long-term, or how the brain might respond during other AI-assisted tasks. 'We don't have any of these answers in this paper,' Kosmyna says. The work was posted ahead of peer review on the preprint server arXiv on 10 June.
On supporting science journalism
If you're enjoying this article, consider supporting our award-winning journalism by subscribing. By purchasing a subscription you are helping to ensure the future of impactful stories about the discoveries and ideas shaping our world today.
Easy essays
Kosmyna's team recruited 60 students, aged 18 to 39, from five universities around the city of Boston, Massachusetts. The researchers asked them to spend 20 minutes crafting a short essay answering questions, such as 'should we always think before we speak?', that appear on Scholastic Assessment Tests, or SATs.
The participants were divided into three groups: one used ChatGPT, powered by OpenAI's large language model GPT-4o, as the sole source of information for their essays; another used Google to search for material (without any AI-assisted answers); and the third was forbidden to go online at all. In the end, 54 participants wrote essays answering three questions while in their assigned group, and then 18 were re-assigned to a new group to write a fourth essay, on one of the topics that they had tackled previously.
Each student wore a commercial electrode-covered cap, which collected electroencephalography (EEG) readings as they wrote. These headsets measure tiny voltage changes from brain activity and can show which broad regions of the brain are 'talking' to each other.
The students who wrote essays using only their brains showed the strongest, widest-ranging connectivity among brain regions, and had more activity going from the back of their brains to the front, decision-making area. They were also, unsurprisingly, better able to quote from their own essays when questioned by the researchers afterwards.
The Google group, by comparison, had stronger activations in areas known to be involved with visual processing and memory. And the chatbot group displayed the least brain connectivity during the task.
More brain connectivity isn't necessarily good or bad, Kosmyna says. In general, more brain activity might be a sign that someone is engaging more deeply with a task, or it might be a sign of inefficiency in thinking, or an indication that the person is overwhelmed by 'cognitive overload'.
Creativity lost?
Interestingly, when the participants who initially used ChatGPT for their essays switched to writing without any online tools, their brains ramped up connectivity — but not to the same level as in the participants who worked without the tools from the beginning.
'This evidence aligns with a worry that many creativity researchers have about AI — that overuse of AI, especially for idea generation, may lead to brains that are less well-practised in core mechanisms of creativity,' says Adam Green, co-founder of the Society for the Neuroscience of Creativity and a cognitive neuroscientist at Georgetown University in Washington DC.
But only 18 people were included in this last part of the study, Green notes, which adds uncertainty to the findings. He also says there could be other explanations for the observations: for instance, these students were rewriting an essay on a topic they had already tackled, and therefore the task might have drawn on cognitive resources that differed from those required when writing about a brand-new topic.
Confoundingly, the study also showed that switching to a chatbot to write an essay after previously composing it without any online tools boosted brain connectivity — the opposite, Green says, of what you might expect. This suggests it could be important to think about when AI tools are introduced to learners to enhance their experience, Kosmyna says. 'The timing might be important.'
Many educational scholars are optimistic about the use of chatbots as effective, personalized tutors. Guido Makransky, an educational psychologist at the University of Copenhagen, says these tools work best when they guide students to ask reflective questions, rather than giving them answers.
'It's an interesting paper, and I can see why it's getting so much attention,' Makransky says. 'But in the real world, students would and should interact with AI in a different way.'
Hashtags
Try Our AI Features
Explore what Daily8 AI can do for you:
Comments
No comments yet...
Related Articles
Yahoo
3 hours ago
- Yahoo
Vantage Data Centers plans $25 billion AI campus in Texas
(Reuters) -Vantage Data Centers said on Tuesday it would spend more than $25 billion to build a 1,200-acre data center campus in Shackelford County, Texas, as surging demand for artificial intelligence infrastructure fuels mega-scale developments. Backed by private equity firm Silver Lake and asset manager DigitalBridge, Vantage said the 1.4-gigawatt campus, dubbed "Frontier", is the largest in its global portfolio. Chatbots such as OpenAI's ChatGPT and Google's Gemini need massive compute, prompting demand for purpose-built data centers. These facilities are costly as they require cutting-edge chips, servers, adequate power and cooling solutions. Companies including Alphabet, Microsoft and Meta Platforms are committing billions of dollars to expand and create their data center facilities. Vantage says the construction of the campus has begun, which will be home to 10 data centers and support ultra-high-density racks exceeding 250 kilowatts each. The first building is due in the second half of next year. Silver Lake was a founding investor in Vantage in 2010. Vantage CEO Sureel Choksi joined the company from Silver Lake in 2013. After exiting Vantage in 2017, Silver Lake said it was invited back on a proprietary basis in 2023 to support capital raising and co-lead a $9.2 billion equity financing with DigitalBridge in 2024. Error in retrieving data Sign in to access your portfolio Error in retrieving data Error in retrieving data Error in retrieving data Error in retrieving data
CNET
3 hours ago
- CNET
Grammarly Pushes Beyond Proofreading With AI-Powered Writing Guidance
Grammarly is expanding beyond its grammar-checking roots. The company has announced the launch of several specialized AI "agents" and a new writing tool called Grammarly Docs, designed to help students and professionals with everything from drafting essays to polishing workplace emails. It's another example of generative AI expanding beyond general-purpose chatbots like ChatGPT and Gemini into more specialized domains. Other examples of gen AI in educational circles include Google's NotebookLM and OpenAI's new study mode for ChatGPT. AI agents are digital helpers that go beyond traditional chatbots to understand context and assist in reaching your goals. Grammarly's AI agents assist by offering feedback, predicting reactions, finding sources and more to increase efficiency in workflows. Read also: Grammarly AI: This Free AI Tool Will Easily Fix Your Grammar What's available now for Grammarly AI The update introduces nine agents that move Grammarly into a more collaborative role. Instead of just correcting grammar or suggesting phrasing, the agents are intended to actively work alongside users. One predicts how a professor or manager might respond to a draft. Another offers an estimated grade based on an uploaded rubric. Others handle citation generation, proofreading, paraphrasing, plagiarism checks and AI detection. The tools are built directly into Docs, a "distraction-free" writing environment where all the agents can be summoned in context, according to the company. As students head back to classrooms and colleges, Grammarly is looking to position itself as a study companion and writing coach rather than merely a browser extension. The company cites research showing that while only a small share of students feel confident using AI in professional settings (18%), most employers expect AI literacy from job candidates. By emphasizing skill-building and responsible use, Grammarly says it wants to bridge that gap rather than simply automate assignments. "The launch of our new agents and AI writing surface marks a turning point in how we build products that anticipate user needs," Luke Behnke, Grammarly's vice president of product management, said in the company's press release. "We're moving beyond simple suggestions to intelligent agents that understand context and actively help users achieve their communication goals." For professionals, Grammarly is marketing the tools as a way to tailor communication for different audiences. The Reader Reactions agent, for example, can highlight whether an email comes across as too vague or too blunt. And the Expert Review tool provides industry-specific feedback without requiring specialized prompts. The launch also marks the debut of Docs as a standalone writing hub. Until now, Grammarly has functioned mostly as a browser extension layered on top of other apps, like Chrome or Google Docs. Grammarly Docs signals a push to keep users inside the platform's own environment, though the company says it will expand agent functionality to the more than half a million apps and sites where its tools already appear. The new features are rolling out immediately for free and premium subscribers, though plagiarism and AI detection remain locked behind the paid plan. Enterprise and education customers will also gain access later this year. Early reactions to Grammary's AI agents Early reactions suggest strong interest from students and educators alike as the company shifts from a grammar checker to a productivity platform. Educators have noted the potential benefits and risks of tools like the AI Grader. Some users on social media welcomed the update as a way to cut through the anxiety of essay writing, while others questioned whether it might make students too dependent on machine feedback. The launch comes just months after Grammarly raised $1 billion to fuel its AI pivot and acquired the email startup Superhuman. Together, those moves point to an ambitious strategy for the company: one that seeks to transform Grammarly from a background utility into a full-fledged productivity suite powered by AI.
Forbes
3 hours ago
- Forbes
The Prompt: Sam Altman Escalates Rivalry With Elon Musk
Welcome back to The Prompt. Elon Musk and Sam Altman speak onstage at the Vanity Fair New Establishment Summit on October 6, 2015 in San Francisco, California, back when they were still friends. (Photo byfor Vanity Fair) Two of the most prominent names in AI, Sam Altman and Elon Musk have been at odds with each other for a while now. From lawsuits (and counterlawsuits) to scathing social media posts, the rivalry of the two Silicon Valley heavyweights has been quite apparent. While their respective companies— OpenAI and xAI— battle it out head to head as competitors, Altman has been developing products and investing in companies that directly compete with many of Musk's businesses, Forbes reported. Altman is backing brain computer interface startup and Neuralink rival Merge Labs. He recently shared his aspirations for an AI-powered social media platform that would directly compete with X. The billionaire CEO is also going after the self-driving market by partnering with Applied Intuition and has invested in a SpaceX competitor that aims to (literally) shoot satellites into orbit with a gigantic gun. Let's get into the headlines. BIG PLAYS Congress passed a law banning TikTok in the U.S. due to national security concerns over its Chinese parent company Bytedance. It's still on people's phones, though, because President Trump has told the Department of Justice to suspend enforcement of the law as terms of a sale to a U.S. company are brokered. Now under a hiatus from regulatory scrutiny, Bytedance has continued to ship a scurry of AI apps ranging from an AI coding tool to image and music generators, Forbes reported. ETHICS+ LAW Meta has permitted its AI chatbots to 'engage a child in a conversation that's romantic or sensual,' according to an internal document that lays out rules of how its bots should interact with people, Reuters reported. The Facebook and Instagram-owner also allows its generative AI assistant, Meta AI, to generate and supply false information, create violent imagery of elders and children and spin up content that argues that 'Black people are dumber than white people.' In response to the report, Meta removed portions of its policies that allowed its chatbots to flirt and engage in romantic roleplay with children. TALENT SHUFFLING Meta has experienced a significant churn among its top-tier AI talent, largely due to a chaotic culture within its generative AI team and a lack of vision, multiple ex-Meta AI researchers told Forbes . The tech giant continues to lose talent, despite a recruiting blitz that has seen it poach talent from OpenAI and other AI juggernauts for its all-star superintelligence team. (A recent example— Joelle Pineau, former VP of AI research at Meta joined Cohere as its Chief AI Officer.) The company's AI arm, which started with the creation of FAIR, has gone through a series of reorganizations. Now with its fresh set of hires that includes ex-Scale AI CEO Alex Wang, Meta reportedly plans yet another shake-up by splitting its current AI division into four parts. AI DEAL OF THE WEEK Enterprise-focused AI startup Cohere has raised $500 million at a $6.8 billion valuation led by Radical Ventures and Inovia Capital. The Canadian startup, which was an early entrant to the generative AI space, recently launched a software offering called North that helps use different large language models to quickly create customized AI systems and automate specific tasks across functions like HR and marketing. Unlike other startups that are chasing the still relatively undefined goal of achieving AGI (an AI system that rivals human intelligence), Cohere is focused on how AI can best be used to increase productivity, Cohere cofounder Nick Frosst told me last week. Plus: Pylon, which is an AI-based customer support system for B2B companies, has raised $31 million in funding co-led by Bain Capital Ventures and Andreessen Horowitz. DEEP DIVE Earlier this year, Scott Rasmussen, the longtime pollster and political commentator, traveled to Bowling Green, Kentucky. After he toured the city, about 65 miles north of Nashville, he returned with a novel idea: use AI to transform polling, a notoriously fickle and imprecise discipline that he had studied for decades. To pursue the project, he teamed up with an unlikely partner — Google. Rasmussen had visited Bowling Green to check out the work of Jigsaw, a think tank inside Google that tackles big societal challenges like online extremism. At the time, it was working with the Kentucky city's local government on an experiment aimed at jumpstarting civic engagement. Jigsaw asked residents to answer questions about the issues they cared most about, from the potential arrival of a Dave & Buster's to the debate over marijuana legalization. From there, it would use a Google AI tool called Sensemaker, built from its language model Gemini, to analyze the answers and separate the residents' disagreements from where they had common ground. The problem with traditional polls, he said, is that closed-ended questions empower the asker to frame or tilt the discussion with yes or no answers, a binary that reduces nuance. 'When you begin to ask people the questions in a different way — or begin to address their opinions in a different way — you hear things you never thought to ask,' he said. The result is an ambitious project: As the United States turns 250-years-old next July, Jigsaw partnered with Rasmussen's Napolitan Institute, a nonprofit dedicated to the future of polling and analysis, on an initiative to use AI in a similar fashion to poll Americans about the future of the country. The project, called We The People, Google exclusively told Forbes , will gather five to 10 people each from all 435 congressional districts in the U.S. to answer questions about what it means to be an American, the most urgent issues facing the country, and where the nation might go from here. 'We want to use AI to give people voice and choice in the world around them,' Yasmin Green, CEO of Jigsaw and a 19-year veteran of Google, told Forbes . 'If people don't feel that they have a voice, or their voice matters to their policymaker, they don't feel that they are enfranchised or have agency.' Read the full story on Forbes . MODEL BEHAVIOR As the AI race heats up, developers and enthusiasts are gambling on which AI model is most likely to come out on top as the 'best AI model of the month,' the Wall Street Journal reported. Some are already minting money by betting against the success of certain model launches like GPT-5 and making hundreds of trades through sites like Kalshi and Polymarket, where people can bet on predictions of real world events.
