Safety
Math for AI safety: an invitation for mathematicians
arXiv:2609.15289v1 Announce Type: cross Abstract: Artificial intelligence threatens to outrun human understanding and control. New mathematics is needed to design AI that is legible, steerable, and co
arXiv:2609.15289v1 Announce Type: cross Abstract: Artificial intelligence threatens to outrun human understanding and control. New mathematics is needed to design AI that is legible, steerable, and cooperative with humanity. I organize this invitation by mathematical field, so you can turn straight to your own: logic and game theory for cooperation; probability for agency and world-models; algebra and representation theory for learned features; analysis and geometry for generalization and training dynamics. Each section ends with an open problem that is accessible to a working mathematician with no prior experience in AI safety.
Related
- Visualizing Uncertainty-to-Action Composition for Human Oversight
- Safe RLHF Beyond Expectation: Stochastic Dominance for Universal Spectral Risk Control
- Context operations to architecture modelling output from large language models and evaluation criteria for their use in systems engineering design
Source: arXiv cs.AI | 2026-09-15