TRIBE v2: Meta introduces AI model that can predict human brain activity

Artificial intelligence research is increasingly moving closer to human neuroscience. Meta has introduced a new AI system designed to predict human brain activity, highlighting how machine learning and brain research are beginning to converge.

The model, called TRIBE v2, analyses patterns in brain activity recorded through functional magnetic resonance imaging (fMRI). According to Meta’s research blog and demonstration page, the system was trained using brain scan data from more than 700 volunteers.

Researchers say the model could help scientists better understand how the brain processes images, sound and language.

What is Meta’s TRIBE v2 AI model?

TRIBE v2 is an AI system designed to interpret patterns in neural activity. It uses machine learning techniques to analyse fMRI scans that record blood flow changes in the brain.

These changes reveal which parts of the brain become active when people see images, listen to sounds or read text. According to Meta researchers, participants in the study were exposed to different forms of content such as:

Images

Audio clips

Written language

The AI model then analysed how the brain responded to each stimulus. Over time, it learned to predict neural activity patterns linked to different types of information.

Meta said the goal is to develop AI systems that better understand how the human brain processes information.

How the model was trained

The system was trained using brain imaging data collected from over 700 volunteers. Functional MRI technology allows researchers to observe brain activity by measuring oxygen levels in different brain regions.

By analysing these signals, the AI system identifies relationships between external stimuli and neural responses. According to Meta’s research explanation, the model can predict how certain sensory inputs such as pictures or language may activate specific brain areas.

Scientists say this approach helps build computational models that simulate aspects of human cognition.

Why companies are studying the brain

Technology companies are increasingly investing in neuroscience research to improve artificial intelligence.

While current AI systems are strong in pattern recognition and data processing, they still struggle with contextual reasoning and flexible understanding areas where the human brain performs far better. By studying neural activity patterns, researchers hope to improve how AI models:

Interpret language

Understand context

Predict human behaviour

Learn from limited information

Meta said the work is part of a broader effort to build AI systems that resemble aspects of human intelligence.

Possible applications in healthcare and neurotechnology

Although the model is still in the research stage, experts say such technology could eventually support several fields.

Potential applications include:

Brain–computer interfaces

Assistive communication tools

Research into neurological disorders

Personalised medical treatments based on brain responses

For example, brain-computer interfaces could allow people with speech or motor impairments to communicate using neural signals.

However, scientists note that the technology is still far from clinical use.

Ethical questions around brain data

Research combining AI and brain signals also raises important ethical questions.

Brain activity data is considered highly sensitive information. Experts warn that strict privacy safeguards will be necessary as the technology develops.

Concerns include:

Data privacy and consent

Potential misuse of neural information

Security of brain-signal datasets

As research continues, policymakers and scientists may need to develop new guidelines governing how neural data can be used.

What this means for AI research

Meta’s TRIBE v2 project shows how AI research is expanding beyond traditional computing tasks. By analysing how the brain reacts to different inputs, scientists hope to create AI systems that process information in more human-like ways.

Although the technology is still experimental, it highlights the growing intersection between neuroscience and artificial intelligence.

As companies continue investing in this field, future AI systems may become better at understanding language, context and human behaviour areas where machines still lag behind people.