Zobrazeno 1 - 10
of 6 692
pro vyhledávání: '"Safety cases"'
Autor:
Cârlan, Carmen, Gomez, Francesca, Mathew, Yohan, Krishna, Ketana, King, René, Gebauer, Peter, Smith, Ben R.
Frontier artificial intelligence (AI) systems present both benefits and risks to society. Safety cases - structured arguments supported by evidence - are one way to help ensure the safe development and deployment of these systems. Yet the evolving na
Externí odkaz:
http://arxiv.org/abs/2412.17618
Autor:
Balesni, Mikita, Hobbhahn, Marius, Lindner, David, Meinke, Alexander, Korbak, Tomek, Clymer, Joshua, Shlegeris, Buck, Scheurer, Jérémy, Stix, Charlotte, Shah, Rusheb, Goldowsky-Dill, Nicholas, Braun, Dan, Chughtai, Bilal, Evans, Owain, Kokotajlo, Daniel, Bushnaq, Lucius
We sketch how developers of frontier AI systems could construct a structured rationale -- a 'safety case' -- that an AI system is unlikely to cause catastrophic outcomes through scheming. Scheming is a potential threat model where AI systems could pu
Externí odkaz:
http://arxiv.org/abs/2411.03336
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, suppor
Externí odkaz:
http://arxiv.org/abs/2410.21572
As AI systems become more advanced, companies and regulators will make difficult decisions about whether it is safe to train and deploy them. To prepare for these decisions, we investigate how developers could make a 'safety case,' which is a structu
Externí odkaz:
http://arxiv.org/abs/2403.10462
Publikováno v:
EPTCS 391, 2023, pp. 83-88
An overview of the process to develop a safety case for an autonomous robot deployment on a nuclear site in the UK is described and a safety case for a hypothetical robot incorporating AI is presented. This forms a first step towards a deployment, sh
Externí odkaz:
http://arxiv.org/abs/2310.02344
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.