If We Succeed
Bibliographic Data
| ID | 9685500 |
|---|---|
| Authors | Russell (0000-0003-0563-1066, corresponding author), Stuart Russell (0000-0003-0282-4970) |
| Year | 2022 |
| Volume | 151 |
| Issue | 2 |
| Pages | 43-57 |
| Publication date | 2022-05-01 |
| Peer Reviewed | Yes |
| Open Access | Yes |
| Type | ARTICLE |
| Venue | Daedalus (JOURNAL) |
| Journal identifiers | ISSN: 0011-5266 • E-ISSN: 1548-6192 |
| Publisher | MIT Press (PUBLISHER • US) |
| DOI | 10.1162/daed_a_01899 |
| OpenAlex | W4226141296 |
| Language | EN |
| Citations received | 2 |
| References cited | 6 |
Since its inception, AI has operated within a standard model whereby systems are designed to optimize a fixed, known objective. This model has been increasingly successful. I briefly summarize the state of the art and its likely evolution over the next decade. Substantial breakthroughs leading to general-purpose AI are much harder to predict, but they will have an enormous impact on society. At the same time, the standard model will become progressively untenable in real-world applications because of the difficulty of specifying objectives completely and correctly. I propose a new model for AI development in which the machine's uncertainty about the true objective leads to qualitatively new modes of behavior that are more robust, controllable, and deferential
Algorithm · Economics · Management science · Mathematical economics · Operations research · State (computer science · Artificial Intelligence · Computer Science · Engineering · Explainable Artificial Intelligence (XAI
| Unique citing works | 2 |
|---|---|
| Citations per year | 0,67 |
| Citation span | 2023 - 2025 (3) |
| Citation velocity | recent |
| Highly cited | No |
| Citation types | Neutral: 2 |