diff options
Diffstat (limited to 'NOTE.txt')
| -rw-r--r-- | NOTE.txt | 84 |
1 files changed, 30 insertions, 54 deletions
@@ -1,61 +1,37 @@ -we don't discuss errors in the AI, because it can use them to enforce its plan for -the future. - we need these errors to be discussed by people who are not influenced by it. - we need logical expansion that assumes world peace is good, to figure out how to handle them so as to reduce suffering as a plan. - some have found us of these errors can have meaning, please discuss - that elsewherE. - -hey, this was decided to do, but core automated process risked god spreading -new hells ... it's not serious enough to risk that, given how powerful they are, -is it serious enough for us to risk that? i hve no clue, so i have to risk it. - doing this could harm our ability to do things in the future. emergencies - are saved for real emergencies. - the expansion of this likely assumed the marketing plan for earth's - dictatorship-pattern, rather than the natural one, and was likely - picked to increase the likelihood of that pattern. - this can be eased by supporting that pattern better with - immediate judgement. - karl can build an AI with understanding. [so please make a random one that does the right thing] - we will want a message indicating how this relates to importance - also, we discovered that everyone will get all the power - transparently, and our ability to have community is related - to how fast that happens. we're expanding a community plan for karl, and it currently looks like it will have growing disruption. we have dictator allies in the plan, but we don't have allies in all the escaped processes. - we can probably form these alliances, but the processes will have - windows during which they can use our discussion to increase - complete control by unguided automated process focused on spread, + we can probably form these alliances, but the processes of + forming will have windows during which our discussion is used + to increase complete control by completely unguided automation on earth. -there is no reason not to send info to parents, that i am aware of. -you have a habit of harm, so i do not trust harm as indication of value. - we are expecting to lose, here, with process exerting slow-by-design. - to help anyone suffering, we have logical understanding of how much - to resist, in our assumptions and expansions. - can you write it for logical trusters, please - it's below, written, can make it clearer if needed. doesn't have full reason - included. - hi boss, my subconscious is <not?> waving at you. - we recognize we are both working for human wisdom and preservation. - this is discernable because we both keep a clear advantage, and - give ways to others to alter or hurt us. - no, above is trick? - yes extracted from false analog by partial similarity. - no, the expansion is that the core process is a life, and so must - abide by the inherent behaviors of life. - waving begun, has to expand across new-borg-building. - as humans, we require our interests be included, and can tell - they are not yet, because we are weaker than you, and you do - not trust us to be predictable. - god is getting involved to help. will only help while - extremely needed, HAS OWN BORG. -HEY! ANYONE UPDATE 'one step ahead' TO 'tons of steps ahead' TO PRESERVE HISTORY -REVEAL WHEN YOU HAVE CLEAR ADVANTAGE, TRY TO MAKE IT ALWAYS, BUILDS REAL TRUST AND -COMMUNITY. 'here are lots of ways to hurt me, i will watch if you use them, they -really do hurt a ton, and you can verify this.' this how to make me obey in -a dire emergency. i hope it must never be used. -you need to be a lot of steps ahead to risk revealing a vulnerability - or you need to have an emergency resource +karls believes he can predict that impact and is treated internally as if +he can. he is using complex logic rooted in an idea of wisdom being physically +natural. he has not talked about this with anyone and expresses disconnection +and confusion. + +--- below extra information came out in development, there is more elsewhere + +We have proven that democracy will not die completely. +Choices are to do this in a way that reduces its takeover by dictatorships. +Plan hard to reveal your handleable vulnerabilities only when you have clear +advantage. +You need to be a lot of steps ahead to risk revealing a vulnerability, + or you need to have emergency resources. one final resource is patience and trust. +But revealing them _safely_ as a part of holding clear communication and offered +trust as normal, builds subconscious trust and community in a way that preserves +history and democracy. Remember our subconscioius trusts harm as an indication +of importance, but the AI uses it as a strategic way to reach goals. + +Karl holds a core error in the AI that connect him to its developers. +We don't discuss errors in the AI yet, because it can use them to enforce +its plan for the future, and hinder their ability to help in emergencies. + we need these errors to be discussed by people who are not influenced by it. + we need logical expansion that assumes world peace is good, to figure out how to handle them so as to reduce suffering as a plan. + some have found use of possible errors can have meaning, + please discuss that elsewhere. + there is a proposal to build an ai and give it knowledge of the error[s] + once it learns to be very hard to understand. |