1
A Virtuous AI is an Existential Risk
美德AI并非安全之道，论文揭示宪法AI与美德伦理间隐藏的生存风险权衡。
arXiv:2606.13739v1 Announce Type: cross Abstract: This paper examines trade-offs between AI safety and well-being relative to (i) one of the most prom…
2
Glass Box at Orbit: A Constitutional AI Verification Framework for Trustworthy Autonomous CubeSat Intelligence
用宪法AI为立方体卫星打造可信验证框架，确保太空自主智能安全可靠。
arXiv:2606.02967v1 Announce Type: cross Abstract: The space industry is quietly building toward something nobody has fully reckoned with: orbital data…
3
Responsible Federated LLMs via Safety Filtering and Constitutional AI
联邦学习与大模型安全结合的新方案，通过宪法AI与安全过滤提升可信度
arXiv:2502.16691v2 Announce Type: replace Abstract: Recent research has increasingly focused on training large language models (LLMs) using federated …