Training AI to be Loyal
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866916625454727168 |
|---|---|
| author | Oh, Sewoong Tyagi, Himanshu Viswanath, Pramod |
| author_facet | Oh, Sewoong Tyagi, Himanshu Viswanath, Pramod |
| contents | Loyal AI is loyal to the community that builds it. An AI is loyal to a community if the community has ownership, alignment, and control. Community owned models can only be used with the approval of the community and share the economic rewards communally. Community aligned models have values that are aligned with the consensus of the community. Community controlled models perform functions designed by the community. Since we would like permissionless access to the loyal AI's community, we need the AI to be open source. The key scientific question then is: how can we build models that are openly accessible (open source) and yet are owned and governed by the community. This seeming impossibility is the focus of this paper where we outline a concrete pathway to Open, Monetizable and Loyal models (OML), building on our earlier work on OML, arXiv:2411.03887(1) , and a representation via a cryptographic-ML library http://github.com/sentient-agi/oml-1.0-fingerprinting . |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_15720 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Training AI to be Loyal Oh, Sewoong Tyagi, Himanshu Viswanath, Pramod Computers and Society Artificial Intelligence Cryptography and Security Machine Learning I.2.6 Loyal AI is loyal to the community that builds it. An AI is loyal to a community if the community has ownership, alignment, and control. Community owned models can only be used with the approval of the community and share the economic rewards communally. Community aligned models have values that are aligned with the consensus of the community. Community controlled models perform functions designed by the community. Since we would like permissionless access to the loyal AI's community, we need the AI to be open source. The key scientific question then is: how can we build models that are openly accessible (open source) and yet are owned and governed by the community. This seeming impossibility is the focus of this paper where we outline a concrete pathway to Open, Monetizable and Loyal models (OML), building on our earlier work on OML, arXiv:2411.03887(1) , and a representation via a cryptographic-ML library http://github.com/sentient-agi/oml-1.0-fingerprinting . |
| title | Training AI to be Loyal |
| topic | Computers and Society Artificial Intelligence Cryptography and Security Machine Learning I.2.6 |
| url | https://arxiv.org/abs/2502.15720 |