AI ALIGNMENT FORUM
AF

Wikitags

AI Safety Cases

Edited by Rauno Arike last updated 19th Nov 2024

A safety case is a structured argument showing that a system is acceptably safe for a specific use in a specific environment. Safety cases typically include:

  • A description of the system's operational context
  • Identification of potential hazards and their consequences
  • A description of the risk controls that mitigate the hazards
  • An account of any residual risk
Subscribe
1
Subscribe
1
Discussion0
Discussion0
Posts tagged AI Safety Cases
15AXRP Episode 45 - Samuel Albanie on DeepMind’s AGI Safety Approach
DanielFilan
2mo
0
5Near- and medium-term AI Control Safety Cases
Martín Soto
9mo
0
71AI companies are unlikely to make high-assurance safety cases if timelines are short
ryan_greenblatt
8mo
4
42Anthropic: Three Sketches of ASL-4 Safety Case Components
Zach Stein-Perlman
10mo
18
54New report: Safety Cases for AI
joshc
1y
5
29Toward Safety Cases For AI Scheming
Mikita Balesni, Marius Hobbhahn
10mo
0
33A sketch of an AI control safety case
Tomek Korbak, joshc, Benjamin Hilton, Buck, Geoffrey Irving
7mo
0
31Notes on control evaluations for safety cases
ryan_greenblatt, Buck, Fabien Roger
2y
0
Add Posts