https://doi.org/10.1140/epjs/s11734-026-02169-2
Review
Promises and performance in brain–machine interfaces: will AI be our saviour?
1
Kavli Institute for Systems Neuroscience, NTNU, Trondheim, Norway
2
Department of Mathematical Sciences, NTNU, Trondheim, Norway
a
This email address is being protected from spambots. You need JavaScript enabled to view it.
b
This email address is being protected from spambots. You need JavaScript enabled to view it.
Received:
5
September
2025
Accepted:
29
January
2026
Published online:
1
April
2026
Abstract
Brain–machine interfaces (BMIs) have advanced rapidly in the past decade, yet translating prototypes into everyday use remains elusive. This review critically compares three different approaches—Meta’s non-invasive neural wristband, the minimal cortically invasive Stentrode of Synchron and the invasive cortical implant of Neuralink. We consider in particular the challenges which Meta must overcome because of the three companies, they are unique in their goal of putting BMIs in the hands of the mass market. Whereas earlier reviews surveyed BMIs more broadly, we will focus on how the interests of each company embody distinct trade-offs along the invasiveness spectrum. We highlight Meta’s advances in large-scale electromyography (EMG) datasets and foundational model approaches to cross-user generalization, Synchron’s clinically validated safety and feasibility in real-world home use, albeit at lower information throughput, and Neuralink’s push for unprecedented channel counts and bandwidth despite biological and regulatory hurdles. By synthesizing technical, regulatory, and practical lessons across these cases, we argue that there has not been a single pathway that has yet solved the dual challenge of high-bandwidth decoding and seamless long-term usability. Our novelty lies in contrasting the consumer-focused ambitions of Meta with the medical-first trajectories of Synchron and Neuralink by drawing out common pitfalls such as calibration demands, signal instability, and hype-driven expectations. Looking ahead, we outline how advances in artificial-intelligence (AI) decoding, hybrid multimodal interfaces, and miniaturized wireless hardware could shift BMIs from niche public demonstrations toward mainstream adoption. In doing so, we position Meta’s wristband not as an end point, but as a pivotal case study—revealing why ambition alone is insufficient and where the field must innovate to close the gap between promise and performance.
© The Author(s) 2026
Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/.
