In this area, we seek proposals that leverage neuroscience and neurotechnology to address AI safety from two angles: making AI systems safer through brain-inspired approaches and enhancing human capabilities to remain relevant alongside increasingly powerful AI.
The human brain remains our only working example of general intelligence that integrates capabilities while maintaining alignment with human values. By studying neural implementations of contextual understanding, empathy, and causal inference, we can develop AI systems with similar beneficial properties. Simultaneously, neurotechnology can help ensure humans maintain meaningful control over advanced AI systems by bridging the potentially growing cognitive gap between human and machine intelligence.
We are interested in promising directions including: using neural data to improve AI alignment by fine-tuning models to match brain activations; developing “lo-fi” brain emulations that capture functional aspects of human cognition; creating secure brain-computer interfaces for effective human-AI collaboration; and designing neuromorphic systems that implement specialized cognitive functions like empathy to complement mainstream AI.
Recent advances have dramatically increased feasibility in these areas. Connectomics costs have fallen; neural and behavioral recording technologies are advancing rapidly, digital twin models are on the horizon and neuroscience-informed AI models already show benefits for robustness and alignment.
Our long-term hope is that this research prevents AI from evolving into black-box systems with alien reasoning, instead grounding development in our understanding of safe, embodied, and socially embedded “human-inspired” cognition. Early investment in open, rigorous neuro-AI research could yield lasting infrastructure for aligning intelligence with human values while maintaining human agency through augmented capabilities and more natural human-AI interaction.
We aim to support functionally grounded “lo-fi” brain emulations that simulate human-like cognition without full structural fidelity.
We welcome proposals that use neural and behavioral data to fine-tune AI models toward safer, more human-compatible behavior.
We seek work on brain-computer interfaces (BCIs) and neurotech that augment human capabilities and enable more natural, high-bandwidth, and interpretable human-AI collaboration.
We support efforts to model AI architectures on biological systems and to apply neuroscience methods to make AI more transparent and human-like.
We prioritize work that grounds advanced AI development in our best understanding of natural intelligence while preserving human agency. Projects should demonstrate a clear path toward safer, more interpretable, and more human-compatible AI systems.
We especially welcome proposals that:
Examples of past projects in this area include:
Massachusetts Institute of Technology
University of Minnesota
University College London
The Society Library
University of Pennsylvania
University of Surrey
Massachusetts Institute of Technology
University College London (Honorary)
Okinawa Institute of Science and Technology
Washington University
Seed funding for a much larger project that involves the “Complete Neuronal Input-Output Functions Project” primarily aims to revolutionize our understanding of brain computation through detailed mapping and modeling of neuronal Input-Output Functions (IOFs). The project’s approach to enhancing AI safety lies in its potential to inform whole brain emulation strategies, which promise to make biological intelligence faster, more interconnected, and safer. By starting with the model organism C. elegans and aiming to control and measure the IOFs of all its neurons, the project plans to build a comprehensive understanding of the causal interactions between neurons. This detailed mapping will provide critical insights into the fundamental computational processes of the brain, which are essential for developing more predictable and controllable AI systems. Moreover, the project proposes a structured collaboration between three key groups focusing on accelerating electrophysiology, advancing molecular data generation, and integrating these with computational models. This collaborative effort is designed not only to push the frontiers of neuroscience but also to create a foundation for safely scaling up AI technologies. By aligning the understanding of neuronal computation with AI development, the project aims to contribute directly to AI safety, ensuring that advances in AI are grounded in a deep, biologically informed understanding of intelligent behavior.
Currently, imaging activity throughout entire mammalian brains is not possible; if this were possible, then radical advances in understanding how mammalian brains compute, including perhaps human brains, would be possible. To enable this, we will develop highly biocompatible silicon nanoparticles that will drastically reduce light scattering in living mammalian brain tissue, enabling much deeper and higher-resolution optical imaging and neural interfacing.
Lo-fi approaches for uploading: developing a Turing test for cloning of biological organisms using High-precision Multi-modal Behavior Modeling (HMBM)
We aim to investigate a neglected prior for AI Alignment called self-other overlap: the model having similar internal representations when it reasons about itself and when it reasons about others. We want to test the hypothesis that inducing self-other overlap is a general, scalable, and transferable method of reducing the risk of deception in RL agents and large language models. We hope that methods that align the behavior of models in distribution such as RLHF, together with methods for honesty like self-other overlap and pressures for coherence, would increase the likelihood that the models are aligned with human values.
Funding for a comprehensive report on brain emulation at human scale, aiming to bring the topic into wider discourse. The project will synthesize cutting-edge research and insights from top labs to create a high-quality, accessible resource that highlights the potential of brain emulation technology, its societal implications, and the progress that could be achieved within the next decade. The report will serve as a catalyst for talent and funding in the field, helping to scale interest and engagement in this transformative technology.
I will demonstrate a novel approach for WBE by employing a computational model of neural development. To this end, I will simulate how a mature brain can be reproduced by simulating its development from a single precursor cell.
This project explores the potential of brain-computer interfaces (BCIs) to enhance AI safety, particularly in the context of AGI and/or ASI within a 5-year horizon. It will assess the technical and economic feasibility of BCIs for real-time human oversight, faster intervention, and improved AI alignment. The goal is to produce a comprehensive review and roadmap, identifying promising pathways for further research and development. By leveraging advances in neural interfaces, this work aims to improve human-AI interaction, reducing risks from misaligned AI behavior in high-stakes scenarios.
I propose development of a novel method (expansion x-ray microtomography) which could put human brain connectomics within reach by reaching nanoscale resolution while vastly decreasing the imaging speed bottleneck. This could lead to advances in understanding of AI-relevant cognitive processes such as empathy, sociality, motivation, and decision making and thus facilitate design of AI with closer alignment to human interests.
