Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2412.01946 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917882860929024 |
|---|---|
| author | Peppin, Aidan Reuel, Anka Casper, Stephen Jones, Elliot Strait, Andrew Anwar, Usman Agrawal, Anurag Kapoor, Sayash Koyejo, Sanmi Pellat, Marie Bommasani, Rishi Frosst, Nick Hooker, Sara |
| author_facet | Peppin, Aidan Reuel, Anka Casper, Stephen Jones, Elliot Strait, Andrew Anwar, Usman Agrawal, Anurag Kapoor, Sayash Koyejo, Sanmi Pellat, Marie Bommasani, Rishi Frosst, Nick Hooker, Sara |
| contents | To accurately and confidently answer the question 'could an AI model or system increase biorisk', it is necessary to have both a sound theoretical threat model for how AI models or systems could increase biorisk and a robust method for testing that threat model. This paper provides an analysis of existing available research surrounding two AI and biorisk threat models: 1) access to information and planning via large language models (LLMs), and 2) the use of AI-enabled biological tools (BTs) in synthesizing novel biological artifacts. We find that existing studies around AI-related biorisk are nascent, often speculative in nature, or limited in terms of their methodological maturity and transparency. The available literature suggests that current LLMs and BTs do not pose an immediate risk, and more work is needed to develop rigorous approaches to understanding how future models could increase biorisks. We end with recommendations about how empirical work can be expanded to more precisely target biorisk and ensure rigor and validity of findings. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_01946 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | The Reality of AI and Biorisk Peppin, Aidan Reuel, Anka Casper, Stephen Jones, Elliot Strait, Andrew Anwar, Usman Agrawal, Anurag Kapoor, Sayash Koyejo, Sanmi Pellat, Marie Bommasani, Rishi Frosst, Nick Hooker, Sara Artificial Intelligence To accurately and confidently answer the question 'could an AI model or system increase biorisk', it is necessary to have both a sound theoretical threat model for how AI models or systems could increase biorisk and a robust method for testing that threat model. This paper provides an analysis of existing available research surrounding two AI and biorisk threat models: 1) access to information and planning via large language models (LLMs), and 2) the use of AI-enabled biological tools (BTs) in synthesizing novel biological artifacts. We find that existing studies around AI-related biorisk are nascent, often speculative in nature, or limited in terms of their methodological maturity and transparency. The available literature suggests that current LLMs and BTs do not pose an immediate risk, and more work is needed to develop rigorous approaches to understanding how future models could increase biorisks. We end with recommendations about how empirical work can be expanded to more precisely target biorisk and ensure rigor and validity of findings. |
| title | The Reality of AI and Biorisk |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2412.01946 |