# NeuroAI for AI Safety

arXiv: https://arxiv.org/abs/2411.18526 · HTML: https://mlsanity.com/paper/2411.18526/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Nov 2024.

## Built on by (most cited first, 11 of 11)

- [Unboxing the Black Box: Mechanistic Interpretability for Algorithmic Understanding of Neural Networks](https://mlsanity.com/paper/2511.19265/) (2025)
- [When Language Models Lose Their Mind: The Consequences of Brain Misalignment](https://mlsanity.com/paper/2603.23091/) (2026)
- [An Affective-Taxis Hypothesis for Alignment and Interpretability](https://mlsanity.com/paper/2505.17024/) (2025)
- [BioBlue: Systematic runaway-optimiser-like LLM failure modes on biologically and economically aligned AI safety benchmarks for LLMs with simplified observation format](https://mlsanity.com/paper/2509.02655/) (2025)
- [Mechanistic Interpretability of Brain-to-Speech Models Across Speech Modes](https://mlsanity.com/paper/2602.01247/) (2026)
- [Robusto-1 Dataset: Comparing Humans and VLMs on real out-of-distribution Autonomous Driving VQA from Peru](https://mlsanity.com/paper/2503.07587/) (2025)
- [BIRD: Behavior Induction via Representation-structure Distillation](https://mlsanity.com/paper/2505.23933/) (2025)
- [Estimating Dimensionality of Neural Representations from Finite Samples](https://mlsanity.com/paper/2509.26560/) (2025)
- [A New Strategy for Artificial Intelligence: Training Foundation Models Directly on Human Brain Data](https://mlsanity.com/paper/2601.12053/) (2026)
- [How Much is Brain Data Worth for Machine Learning?](https://mlsanity.com/paper/2605.09243/) (2026)
- [World models of environment, agent and joint agent-environment systems](https://mlsanity.com/paper/2608.20401/) (2026)

## Abstract (arXiv)

As AI systems become increasingly powerful, the need for safe AI has become more pressing. Humans are an attractive model for AI safety: as the only known agents capable of general intelligence, they perform robustly even under conditions that deviate significantly from prior experiences, explore the world safely, understand pragmatics, and can cooperate to meet their intrinsic goals. Intelligence, when coupled with cooperation and safety mechanisms, can drive sustained progress and well-being. These properties are a function of the architecture of the brain and the learning algorithms it implements. Neuroscience may thus hold important keys to technical AI safety that are currently underexplored and underutilized. In this roadmap, we highlight and critically evaluate several paths toward AI safety inspired by neuroscience: emulating the brain's representations, information processing, and architecture; building robust sensory and motor systems from imitating brain data and bodies; fine-tuning AI systems on brain data; advancing interpretability using neuroscience methods; and scaling up cognitively-inspired architectures. We make several concrete recommendations for how neuroscience can positively impact AI safety.