•

- In theory,
~~modelling~~the control of system A over system B means that A can influence system B to achieve A’s desired subset of state space [Source: https://arxiv.org/pdf/2109.00484.pdf]. - In practice,
~~engineering~~to engineer control of AGI requires simulating or detecting any unsafe effects internally, and then preventing or correcting those effects externally.

- Theoretical limits to controlling any AGI using any method of
~~engineerable control of AGI.~~causation. - Threat models of AGI convergent dynamics that are impossible to control (by 1.).
- Impossibility theorems, by contradiction of 'long-term AGI safety' with convergence
~~results~~result (2.)

- Theoretical limits of engineerable control of AGI.
- Threat models of AGI convergent dynamics that are impossible to control (by 1.).
- Impossibility theorems, by contradiction of 'long-term AGI safety' with convergence
~~result~~results (2.)

- Theoretical limits of engineerable control of AGI.
- Threat models of AGI convergent dynamics that are
~~strictly uncontrollable~~impossible to control (by 1.). - Impossibility theorems, by contradiction of 'long-term AGI safety' with convergence result
~~(from 2.~~(2.)

*'AGI convergent dynamic that is strictly uncontrollable'impossible to control':*

- Theoretical limits of engineerable control of AGI.
- Threat models of
~~an out-of-control~~AGI convergent dynamics that are strictly uncontrollable (by 1.)~~AGI convergent dynamic.~~. - Impossibility theorems, by contradiction of 'long-term AGI safety'
~~proposition~~with convergence result (from 2.)

*' Out-of-control AGI convergent dynamic'dynamic that is strictly uncontrollable':*

Ambient conditions/contexts around planet Earth ~~that are caused~~changed by the operation of AGI fall within the environmental range that humans need to survive (a minimum-threshold definition).

The research field AGI Limits of Engineerable Control & Safety Impossibility Theorems (AGILECSIT) has the purpose of verifying (both the empirical soundness of premises and ~~formal ~~validity of formal reasoning of):

*' out-Out-of-control AGI convergent dynamic':*

- Theoretical limits of engineerable control of AGI.
- Threat models of
~~non-controllable~~an out-of-control (by 1.) AGI convergent~~dynamics of AGI.~~dynamic. - Impossibility theorems, by contradiction of 'long-term AGI safety' proposition with
~~results 1. &~~result 2.

*' Non-controllableout-of-control AGI convergent dynamics of AGI'dynamic':*

- In theory, modelling control of system A over system B means that A can influence system B to achieve A’s desired subset of state space
~~(Source:~~[Source: https://arxiv.org/pdf/2109.00484.pdf~~)~~]. - In practice, engineering control of AGI requires simulating or detecting any unsafe effects internally, and then preventing or correcting those effects externally.

~~(~~[Source: https://mflb.com/ai_alignment_1/si_safety_qanda_out.html#p3~~)~~]

- multiple domains of sense/action.
- intrinsic non-reducible possibility for self-modification;.
- and that/therefore; that the meta-algorithm is effectively arbitrary; hence;
~~.~~ - that it is inherently undecidable as to whether all aspects of its own self agency/intention are fully defined by only its builders/developers/creators.

Ambient conditions/contexts around planet Earth that are caused by the operation of AGI fall within the environmental ~~ranges~~range that humans need to survive (a minimum-threshold definition).

Ambient conditions/contexts around planet Earth that are caused by the operation of AGI fall within the environmental ranges that humans need to survive (a minimum-threshold definition).

Ambient conditions/contexts around planet Earth that are caused by the operation of AGI fall within environmental ~~range~~ranges that humans need to survive (a minimum-threshold definition).

*'Non-controllable convergent dynamics of AGI':*

Iterated interactions of AGI internals (with connected surroundings of environment) that converge on (unsafe) conditions, where the space of interactions falls outside even one theoretical limit of control.

*'Control:'*

~~'Non-controllable convergent dynamics of AGI':~~

~~Iterated interactions of AGI internals (with connected surroundings of environment) that converge on (unsafe) conditions, where the space of interactions falls outside even one theoretical limit of control.~~

*' UncontrollableNon-controllable convergent dynamics of AGI':*

- Theoretical limits of engineerable control of AGI.
- Threat models of
~~uncontrollable~~non-controllable convergent dynamics of AGI. - Impossibility theorems, by contradiction of 'long-term AGI safety' proposition with results 1. & 2.

- Theoretical limits of
~~the~~engineerable control of AGI. - Threat models of uncontrollable convergent dynamics of AGI.
- Impossibility theorems, by contradiction of 'long-term AGI safety' proposition with results 1. & 2.

The research field AGI Limits of Engineerable Control & Safety Impossibility Theorems (AGILECSIT) has the purpose of verifying ~~(the~~(both the empirical soundness of premises and formal validity of reasoning of):

*' Control'Control:'*

~~action.~~action;~~.~~