HOUSE_OVERSIGHT_013126.jpg
1.93 MB
Extraction Summary
0
People
2
Organizations
0
Locations
0
Events
0
Relationships
3
Quotes
Document Information
Type:
Academic paper / book chapter (house oversight committee production)
File Size:
1.93 MB
Summary
A page from an academic text (likely a book chapter titled 'The Engineering and Development of Ethics') discussing Artificial General Intelligence (AGI). The text outlines risks of human-like ethical systems in AGI and proposes an explicit goal system (referencing 'CogPrime' and 'Ubergoals'). It also discusses 'Ethical Synergy' relating to episodic, sensorimotor, and declarative memory. The document bears a House Oversight Bates stamp, suggesting it was collected during an investigation, likely related to Epstein's funding of scientific research or AGI projects.
Organizations (2)
| Name | Type | Context |
|---|---|---|
| CogPrime |
Referenced as the system the authors are working on, utilizing 'Ubergoals'.
|
|
| House Oversight Committee |
Implied by the Bates stamp 'HOUSE_OVERSIGHT_013126'.
|
Key Quotes (3)
"Humans are not all that consistently ethical, so that creating AGI systems potentially much more practically powerful than humans, but with closely humanlike ethical, motivational and goal systems, could in fact be quite dangerous"Source
HOUSE_OVERSIGHT_013126.jpg
Quote #1
"The course we tentatively recommend, and are following in our own work, is to develop AGI systems with explicit, hierarchically-dominated goal systems."Source
HOUSE_OVERSIGHT_013126.jpg
Quote #2
"One of the more novel ideas presented in this chapter is that different types of ethical intuition may be associated with different types of memory"Source
HOUSE_OVERSIGHT_013126.jpg
Quote #3
Discussion 0
No comments yet
Be the first to share your thoughts on this epstein document