Safety cases for frontier AI
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909369069731840 |
|---|---|
| author | Buhl, Marie Davidsen Sett, Gaurav Koessler, Leonie Schuett, Jonas Anderljung, Markus |
| author_facet | Buhl, Marie Davidsen Sett, Gaurav Koessler, Leonie Schuett, Jonas Anderljung, Markus |
| contents | As frontier artificial intelligence (AI) systems become more capable, it becomes more important that developers can explain why their systems are sufficiently safe. One way to do so is via safety cases: reports that make a structured argument, supported by evidence, that a system is safe enough in a given operational context. Safety cases are already common in other safety-critical industries such as aviation and nuclear power. In this paper, we explain why they may also be a useful tool in frontier AI governance, both in industry self-regulation and government regulation. We then discuss the practicalities of safety cases, outlining how to produce a frontier AI safety case and discussing what still needs to happen before safety cases can substantially inform decisions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_21572 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Safety cases for frontier AI Buhl, Marie Davidsen Sett, Gaurav Koessler, Leonie Schuett, Jonas Anderljung, Markus Computers and Society As frontier artificial intelligence (AI) systems become more capable, it becomes more important that developers can explain why their systems are sufficiently safe. One way to do so is via safety cases: reports that make a structured argument, supported by evidence, that a system is safe enough in a given operational context. Safety cases are already common in other safety-critical industries such as aviation and nuclear power. In this paper, we explain why they may also be a useful tool in frontier AI governance, both in industry self-regulation and government regulation. We then discuss the practicalities of safety cases, outlining how to produce a frontier AI safety case and discussing what still needs to happen before safety cases can substantially inform decisions. |
| title | Safety cases for frontier AI |
| topic | Computers and Society |
| url | https://arxiv.org/abs/2410.21572 |