| Both sides previous revisionPrevious revisionNext revision | Previous revision |
| public:t-709-aies-2024:aies-2024:autonomy-meaning [2024/10/23 21:43] – [Understanding] thorisson | public:t-709-aies-2024:aies-2024:autonomy-meaning [2024/10/23 21:45] (current) – [Meaning] thorisson |
|---|
| | Producing Meaning | Meaning is produced through a //process of understanding// using reasoning over causal relations, to produce implications in the //now//. \\ As time passes, meaning changes and must be re-computed. | | | Producing Meaning | Meaning is produced through a //process of understanding// using reasoning over causal relations, to produce implications in the //now//. \\ As time passes, meaning changes and must be re-computed. | |
| | Causal Relations | The relationship between two or more differentiable events such that one of them can (reasonably reliably) produce the other. \\ One event **E**, the //cause//, must come before another event **E'**, the //effect//, where **E** can (reasonably reliably) be used to produce **E'**. | | | Causal Relations | The relationship between two or more differentiable events such that one of them can (reasonably reliably) produce the other. \\ One event **E**, the //cause//, must come before another event **E'**, the //effect//, where **E** can (reasonably reliably) be used to produce **E'**. | |
| | Theory of Foundational Meaning | Foundational meaning is the meaning of anything to an agent. \\ Meaning is generated through a process when causal-relational models are used to compute the //implications// of some action, state, event, etc. \\ Any meaning-producing agent extracts meaning when the implications //interact with its goals// in some way (preventing them, enhancing them, shifting them, ...). | | | \\ Foundational Meaning | Foundational meaning is the meaning of anything to an agent - often contrasted with "semantic meaning" or "symbolic meaning", which is the meaning of symbols or language. \\ The latter rests on the former. \\ Meaning is generated through a process when causal-relational models are used to compute the //implications// of some action, state, event, etc. \\ Any meaning-producing agent extracts meaning when the implications //interact with its goals// in some way (preventing them, enhancing them, shifting them, ...). | |
| |
| \\ | \\ |
| | What Does It Mean? | No well-known scientific theory exists. \\ Normally we do not hand control of anything over to anyone who doesn't understand it. All other things being equal, this is a recipe for disaster. | | | What Does It Mean? | No well-known scientific theory exists. \\ Normally we do not hand control of anything over to anyone who doesn't understand it. All other things being equal, this is a recipe for disaster. | |
| | Evaluating Understanding | Understanding any **X** can be evaluated along four dimensions: \\ 1. Being able to predict **X**, \\ 2. being able to achieve goals with respect to **X**, \\ 3. being able to explain **X**, and \\ 4. being able to "re-create" **X** ("re-create" here means e.g. creating a simulation that produces **X** and many or all its side-effects.) | | | Evaluating Understanding | Understanding any **X** can be evaluated along four dimensions: \\ 1. Being able to predict **X**, \\ 2. being able to achieve goals with respect to **X**, \\ 3. being able to explain **X**, and \\ 4. being able to "re-create" **X** ("re-create" here means e.g. creating a simulation that produces **X** and many or all its side-effects.) | |
| | In AI | Understanding as a concept has been neglected in AI. \\ Contemporary AI systems do not //understand//. \\ The concept seems crucial when talking about human intelligence; the concept holds explanatory power - we do not assign responsibilities for a task to someone or something with a demonstrated lack of understanding of the task. Moreover, the level of understanding can be evaluated. \\ Understanding of a particular phenomenon **P** is the potential to perform actions and answer questions with respect to **P**. Example: Which is heavier, 1kg of iron or 1kg of feathers? || | | \\ \\ In AI | Understanding as a concept has been neglected in AI. \\ Contemporary AI systems do not //understand//. \\ The concept seems crucial when talking about human intelligence; the concept holds explanatory power - we do not assign responsibilities for a task to someone or something with a demonstrated lack of understanding of the task. Moreover, the level of understanding can be evaluated. \\ Understanding of a particular phenomenon **P** is the potential to perform actions and answer questions with respect to **P**. Example: Which is heavier, 1kg of iron or 1kg of feathers? || |
| | Bottom Line | Can't talk about intelligence without talking about understanding. \\ Can't talk about understanding without talking about meaning. | | | Bottom Line | Can't talk about intelligence without talking about understanding. \\ Can't talk about understanding without talking about meaning. | |
| |
