User Tools

Site Tools


public:t-709-aies-2025:aies-2025:trust_explanation_meaning

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revisionPrevious revision
Next revision
Previous revision
public:t-709-aies-2025:aies-2025:trust_explanation_meaning [2025/08/26 08:39] – [Engineered / Earned Trustworthiness] thorissonpublic:t-709-aies-2025:aies-2025:trust_explanation_meaning [2025/08/28 10:10] (current) leonard
Line 1: Line 1:
-[[/public:t-713-mers:mers-25:main|T-713-MERS-2025 Main]] \\ +[[/public:t-709-aies:aies-25:main|T-709-AIES-2025 Main]] \\ 
-[[/public:t-713-mers:mers-25:lecture_notes|Link to Lecture Notes]]+[[/public:t-709-aies:aies-25:lecture_notes|Link to Lecture Notes]]
  
 \\ \\
Line 28: Line 28:
 |  What It Is  | The ability of a machine to always return the same - or categorically similar - answer to the same - and/or categorically similar - input.   | |  What It Is  | The ability of a machine to always return the same - or categorically similar - answer to the same - and/or categorically similar - input.   |
 |  Why It Is Important  | Simple AI algorithms (e.g. reinforcement learning, auto-correlation, decision trees, etc.) are very good in this respect, delivering high reliability. Because they are simple, and their environment is oversimplified, their reliability to can be engineered up front. Near-human-level AI -- or adaptive autonomous machines (AAMs) -- on the other hand, have the same limitations as humans and animals in this respect, i.e. reliability is a challenge, and no guarantees can be given.   | |  Why It Is Important  | Simple AI algorithms (e.g. reinforcement learning, auto-correlation, decision trees, etc.) are very good in this respect, delivering high reliability. Because they are simple, and their environment is oversimplified, their reliability to can be engineered up front. Near-human-level AI -- or adaptive autonomous machines (AAMs) -- on the other hand, have the same limitations as humans and animals in this respect, i.e. reliability is a challenge, and no guarantees can be given.   |
-|  Human-Level AI  | To make AAMs reliable is important because without reliability they cannot be trusted, and hence would defeat most of the purpose for creating them in the first place. (One method for addressing this is through autonomous iterative micro-model generation and refinement.)   | 
-|  Achieving Reliabile AI  | Requires **predictability**. Predictability requires sorting out //causal relations// (without these we can never be sure what lead to what).   | 
 |  Predictability is Hard to Achieve  | In a growing, developing system that is adapting and learning (3 or 4 levels of detail of dynamical relations!) achieving predictability can only be achieved by **abstraction**: Moving up to the next level of detail; e.g. "I cannot be sure //what exactly// I will eat for dinner (one level of detail), but I can be pretty sure that I //will// eat dinner (more coarse-grain level)"   | |  Predictability is Hard to Achieve  | In a growing, developing system that is adapting and learning (3 or 4 levels of detail of dynamical relations!) achieving predictability can only be achieved by **abstraction**: Moving up to the next level of detail; e.g. "I cannot be sure //what exactly// I will eat for dinner (one level of detail), but I can be pretty sure that I //will// eat dinner (more coarse-grain level)"   |
-|  Achieving Abstraction  | Can be done through hierarchy (but it needs to be //dynamic// - i.e. tailored to its intended usage, as the circumstances call for - because the world has too complex combinatorics to store precomputed hierarchies for everything).   | +|  Producing Abstraction  | Can be done through hierarchy (but must be //dynamic// - i.e. dynamically adjusted to its intended usage, as the circumstances call for - because the world has too complex combinatorics to store precomputed hierarchies for everything).   | 
-\\ +|  Human-Level AI  | To make AAMs reliable is important because without reliability they cannot be trusted, and hence would defeat most of the purpose for creating them in the first place. (One method for addressing this is through autonomous iterative micro-model generation and refinement.)   | 
 +|  Achieving Reliabile AI  | Requires **predictability**. Predictability requires sorting out //causal relations// (without these, neither we nor the system can never be sure what leads to what, precluding reliability).   |
  
 +\\
 \\ \\
  
Line 41: Line 40:
 |  What It Is  | The ability of a machine's owner to trust that the machine will do what it is supposed to do.   | |  What It Is  | The ability of a machine's owner to trust that the machine will do what it is supposed to do.   |
 |  Why It Is Important  | Any machine created by humans is created for a purpose. The more reliably it does its job (and nothing else) the more trustworthy it is. Trusting simple machines like thermostats involves mostly durability, since they have very few open variables (unbound variables at time of manufacture).   | |  Why It Is Important  | Any machine created by humans is created for a purpose. The more reliably it does its job (and nothing else) the more trustworthy it is. Trusting simple machines like thermostats involves mostly durability, since they have very few open variables (unbound variables at time of manufacture).   |
-|  Human-Level AI  | To make human-level AI trustworthy is very different from creating simple machines because so many variables are unbound at manufacture time. What does trustworthiness mean in this context? We can look at human trustworthiness: Numerous methods exist for ensuring trustworthiness (license to drive, air traffic controller training, certification programs, etc.). We can have the same certification programs for all humans because their principles of operation are shared at multiple levels of detail (biology, sociology, psychology). For an AI this is different because the variability in the makeup of the machines is enormous. This makes trustworthiness of AI robots a complex issue.   | 
-|  To Achieve Trustworthiness  | Requires **reliability**, and **predictability** at multiple levels of operation. Trustworthiness can be ascertained through special certification programs geared directly at the **kind of robot/AI system in question** (kind of like certifying a particular horse as safe for a particular circumstance and purpose, e.g. horseback riding kids).   | 
 |  Trustworthiness Methods...  | ...for AI are in their infancy.     | |  Trustworthiness Methods...  | ...for AI are in their infancy.     |
 +|  Human-Level AI  | Making human-level AI trustworthy is very different from creating simple machines because so many variables are unbound at manufacturing time. What does trustworthiness mean in this context? We can look at human trustworthiness: Numerous methods exist for ensuring trustworthiness (license to drive, air traffic controller training, certification programs, etc.). We can have the same certification programs for all humans because their principles of operation are shared at multiple levels of detail (biology, sociology, psychology). \\ For an AI this is different because the variability in the makeup of the machines is enormous. This makes trustworthiness of AI a challenging issue.   |
 +|  To Achieve Trustworthiness  | Requires **reliability**, and **predictability** at multiple levels of operation. Trustworthiness can be ascertained through special certification programs geared directly at the **kind of robot/AI system in question** (kind of like certifying a particular horse as safe for a particular circumstance and purpose, e.g. horseback riding kids).   |
  
 +
 +\\
 +\\
 \\ \\
 \\ \\
/var/www/cadia.ru.is/wiki/data/attic/public/t-709-aies-2025/aies-2025/trust_explanation_meaning.1756197599.txt.gz · Last modified: 2025/08/26 08:39 by thorisson

Donate Powered by PHP Valid HTML5 Valid CSS Driven by DokuWiki