Sound Research WIKINDX
Sound Research WIKINDX |
|
 |
|
Silver, D., & Sutton, R. S. Welcome to the era of experience. In Designing an Intelligence. Cambridge, Massachusetts: MIT Press. Added by: Mark Grimshaw-Aagaard (11/18/25, 10:18 AM) Last edited by: Mark Grimshaw-Aagaard (11/19/25, 2:59 AM) |
 |
| Resource type: Book Chapter Language: en: English BibTeX citation key: Silver Email resource to friend View all bibliographic details  |
Categories: AI/Machine Learning Keywords: Artificial creativity, Artificial Intelligence Creators: Silver, Sutton Publisher: MIT Press (Cambridge, Massachusetts) Collection: Designing an Intelligence |
Views: 9/17
|
| Abstract |
|
"We stand on the threshold of a new era in artificial intelligence that promises to achieve an unprecedented level of ability. A new generation of agents will acquire superhuman capabilities by learning predominantly from experience. This note explores the key characteristics that will define this upcoming era."
Added by: Mark Grimshaw-Aagaard |
| Notes |
|
PDF preprint (not all book details available).
Quite utopian. Added by: Mark Grimshaw-Aagaard Last edited by: Mark Grimshaw-Aagaard |
| Quotes |
|
p. 1
"To progress significantly further, a new source of data is required. This data must be generated in a way that continually improves as the agent becomes stronger; any static procedure for synthetically generating data will quickly become outstripped. This can be achieved by allowing [AI/LLM] agents to learn continually from their own experience, i.e., data that is generated by the agent interacting with its environment. AI is at the cusp of a new period in which experience will become the dominant medium of improvement and ultimately dwarf the scale of human data used in today’s systems."
Added by: Mark Grimshaw-Aagaard
(2025-11-18 10:29:09)
|
|
p. 3
"Human-centric LLMs typically optimise for rewards based on human prejudgement: an expert observes the agent’s action and decides whether it is a good action, or picks the best agent action among multiple alternatives. For example, an expert may judge a health agent’s advice, an educational assistant’s teaching, or a scientist agent’s suggested experiment. The fact that these rewards or preferences are determined by humans in absence of their consequences, rather than measuring the effect of those actions on the environment, means that they are not directly grounded in the reality of the world."
Added by: Mark Grimshaw-Aagaard
(2025-11-18 10:38:24)
|
|
p. 5
Where LLMs can act as a universal computer, "the principle of a universal computer only addresses the internal computation of the agent; it does not connect it to the realities of the external world. An agent trained to imitate human thoughts or even to match human expert answers may inherit fallacious methods of thought deeply embedded within that data, such as flawed assumptions or inherent biases. For example, if an agent had been trained to reason using human thoughts and expert answers from 5,000 years ago it may have reasoned about a physical problem in terms of animism; 1,000 years ago it may have reasoned in theistic terms; 300 years ago it may have reasoned in terms of Newtonian mechanics; and 50 years ago in terms of quantum mechanics. Progressing beyond each method of thought required interaction with the real world: making hypotheses, running experiments, observing results, and updating principles accordingly. Similarly, an agent must be grounded in real-world data in order to overturn fallacious methods of thought. This grounding provides a feedback loop, allowing the agent to test its inherited assumptions against reality and discover new principles that are not limited by current, dominant modes of human thought. Without this grounding, an agent, no matter how sophisticated, will become an echo chamber of existing human knowledge."
Added by: Mark Grimshaw-Aagaard
(2025-11-18 10:45:40)
|