liveBook · Manning

Incomputability

As explained in Sutskever's List

The property of a function or object not being exactly computable by any algorithm on a general-purpose computational model.

Incomputability marks a boundary between an ideal formal agent and an implementable system. AIXI’s theoretical results concern an agent that cannot be built, leaving a gap between theory and engineering. section 9.2.6

AIXI

AIXI illustrates how an incomputable agent can support theoretical arguments without offering an implemented system that can succeed or fail empirically. section 9.2.6

How Sutskever's List covers it

How deep it goes
States that AIXI is incomputable and theoretical, without detailing the computing results behind that conclusion.
Examples
Uses AIXI to contrast a theoretical agent with empirical AI systems.
What you can do after
Evaluate the gap between theoretical results about AIXI and implementable AI systems.
How it connects
Connects incomputability to AIXI and superintelligence.
Cover of Sutskever's List
liveBookmanning.com
Read Sutskever's List on liveBook Get the book at manning.com

Related concepts

This explainer was generated by Manning's knowledge graph from the text of Sutskever's List. The section links point to the parts of the book it draws on.