{"id":11315,"date":"2025-03-04T10:00:00","date_gmt":"2025-03-04T09:00:00","guid":{"rendered":"https:\/\/haimagazine.com\/uncategorized\/a-step-away-from-telepathy\/"},"modified":"2025-06-26T15:11:08","modified_gmt":"2025-06-26T13:11:08","slug":"a-step-away-from-telepathy","status":"publish","type":"post","link":"https:\/\/haimagazine.com\/en\/ai-industry\/a-step-away-from-telepathy\/","title":{"rendered":"\ud83d\udd12 A step away from telepathy"},"content":{"rendered":"

In Christopher Nolan’s Inception<\/em>, characters delve into other people’s dreams to explore the deepest recesses of their minds. The plot, which at the time of the film’s release seemed like an artistic fantasy, is starting to look increasingly more realistic. We are approaching a point where we’ll be able to read human thoughts.<\/p>

Researchers at the University of Texas at Austin<\/mark><\/a> have developed a semantic decoder that converts brain activity into a stream of text, thereby enabling communication without the need to speak or write. And the best is that it’s all done without needing to implant any devices!<\/p>

A breakthrough in brain-to-text technology<\/strong><\/h4>

The system uses artificial intelligence and functional magnetic resonance imaging (fMRI) (I wrote more about this imaging technique here<\/mark><\/a>) to analyze brain activity. Until now, training AI to recognize a person’s thoughts required up to 16 hours. Today, it only takes one hour.<\/p>

During training sessions, participants lie in an fMRI scanner and listen to podcasts or watch movies, while AI learns how their brain responds to specific words and contexts. Importantly, the decoder doesn’t reproduce thoughts word for word, but generates a paraphrase that conveys the general meaning of the message.<\/p>

The most surprising thing is that the decoder can operate even when the user is watching a silent movie\u2014it predicts words related in meaning and “understands” the visual context. This means that AI not only interprets language but also reads the intentions behind the observed scenes.<\/p>

Moreover, the system doesn’t rely on a single, specific brain area. If a part of it is damaged, for instance, by a stroke, AI can still operate using other regions. This is a breakthrough for people with aphasia and other language disorders, as it gives them a real chance to regain communication abilities.<\/p>

“We can recover the overall idea… and see how the idea evolves, even if the exact words get lost. We think that the decoder represents something deeper than languages\u201d \u2013 explains Dr. Alexander Huth, main author of the study, in the pages of “Nature Neuroscience”<\/mark><\/a>.<\/p>

Different paths to the same goal<\/strong><\/h4>

The world of brain-computer interfaces (BCI) offers several different approaches to thought communication. How does the new decoder stack up against other technologies?<\/p>

You might think that the semantic decoder competes with Elon Musk’s Neuralink, but they’re entirely different directions. Neuralink relies on implanted chips that read neuron activity and allow to control devices through thoughts. It’s like a wireless mouse that we move with our brain.<\/p>

The semantic decoder is non-invasive, meaning there’s no need to implant anything, but its accuracy is currently unstable. On the other hand, Neuralink offers precision, but requires brain surgery. Choosing between them is like deciding: MRI or brain surgery?<\/p>

Mobility is also an issue. fMRI scanners are huge and definitely not suitable for everyday use, but the research team is working on making this technology smaller.<\/p>

There are also solutions like Cyber-Eye<\/mark><\/a> or BrainGate<\/mark><\/a>, which help paralyzed people communicate with their environment. These technologies follow the eyeball movement or analyze EEG (the brain’s electrical activity). However, they require long training and precise control.<\/p>

What will the future bring?<\/strong><\/h4>

Will we write emails just by thinking any time soon? For now, it’s still a thing of the future. The semantic decoder still needs to overcome issues with precision and miniaturizing complex fMRI scanners, while Neuralink must break through ethical and technological barriers associated with implanting chips, and Cyber-Eye and other eye-tracking systems have their limitations.<\/p>

However, one thing is certain\u2014the line between thought and technology is increasingly blurring, and brain-computer interfaces are becoming more sophisticated every year.<\/p>","protected":false},"excerpt":{"rendered":"

Imagine a technology that transforms your thoughts into text without uttering a single word\u2014thanks to AI and semantic decoders, it’s already a reality that’s changing the future of communication.<\/p>\n","protected":false},"author":234,"featured_media":9051,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"rank_math_lock_modified_date":false,"footnotes":""},"categories":[783,790],"tags":[83,447,736,735,737,734],"popular":[],"difficulty-level":[36],"ppma_author":[544],"class_list":["post-11315","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-ai-industry","category-health-medicine","tag-ai","tag-ai-4","tag-brain-waves","tag-fmri-2","tag-neuralink-2","tag-semantic-decoder","difficulty-level-easy"],"acf":[],"authors":[{"term_id":544,"user_id":234,"is_guest":0,"slug":"joanna-kostecka","display_name":"Joanna Kostecka","avatar_url":"https:\/\/secure.gravatar.com\/avatar\/ae43ac99602c46ef6be2602397c7de5877435d3d69dbab3f38579670340b696e?s=96&d=mm&r=g","first_name":"Joanna","last_name":"Kostecka","user_url":"","job_title":"","description":"Z wykszta\u0142cenia polonistka, graficzka, marketingowiec i wdro\u017ceniowiec rozwi\u0105za\u0144 AI. Prezeska Fundacji Fabryka Dobrych Projekt\u00f3w, propagatorka inkluzywno\u015bci. Entuzjastka AI i VR, szczeg\u00f3lnie w obszarze medycyny i healthcare."}],"_links":{"self":[{"href":"https:\/\/haimagazine.com\/en\/wp-json\/wp\/v2\/posts\/11315","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/haimagazine.com\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/haimagazine.com\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/haimagazine.com\/en\/wp-json\/wp\/v2\/users\/234"}],"replies":[{"embeddable":true,"href":"https:\/\/haimagazine.com\/en\/wp-json\/wp\/v2\/comments?post=11315"}],"version-history":[{"count":1,"href":"https:\/\/haimagazine.com\/en\/wp-json\/wp\/v2\/posts\/11315\/revisions"}],"predecessor-version":[{"id":11316,"href":"https:\/\/haimagazine.com\/en\/wp-json\/wp\/v2\/posts\/11315\/revisions\/11316"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/haimagazine.com\/en\/wp-json\/wp\/v2\/media\/9051"}],"wp:attachment":[{"href":"https:\/\/haimagazine.com\/en\/wp-json\/wp\/v2\/media?parent=11315"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/haimagazine.com\/en\/wp-json\/wp\/v2\/categories?post=11315"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/haimagazine.com\/en\/wp-json\/wp\/v2\/tags?post=11315"},{"taxonomy":"popular","embeddable":true,"href":"https:\/\/haimagazine.com\/en\/wp-json\/wp\/v2\/popular?post=11315"},{"taxonomy":"difficulty-level","embeddable":true,"href":"https:\/\/haimagazine.com\/en\/wp-json\/wp\/v2\/difficulty-level?post=11315"},{"taxonomy":"author","embeddable":true,"href":"https:\/\/haimagazine.com\/en\/wp-json\/wp\/v2\/ppma_author?post=11315"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}