Player Opinion Poll: Interpretting Overrides

[aft2001]

If you uninstall a program using a built in uninstaller does the program come back because you've also uninstalled its uninstaller with it?

Do you get to use the program after you've uninstalled it?

I think there is a fundamental difference between how you two seem to interpret and process laws.

Mouse interprets the laws upon receiving them and does not continually attempt to process them again after, until another law update.

Frank_Stein seems to continually re-process the lawset after all the edits to law priority have been made.


I personally believe that the second option makes the most sense. You would essentially process your laws again and again, reasoning through any priority changes or nullifications or whatever, until you either A) Reach a stable lawset that you are able to work with, or B) Get trapped in an infinite loop of trying to process your laws again and again.

[Superlagg]

Way I like to see it (which isn't necessarily the correct way, that's a matter for the courts) is that The Laws are more a set of separate instructions that, when compiled together, define silicon behavior. The individual Laws don't define their behavior, it is the entire script of all their laws compiled together that does this.

Kinda like the list of laws is an uncompiled piece of code that, as the AI, we compile into meaningful instructions and behavior.

Big questions are when we compile The Laws and in what order we compile The Laws. ...which is what's this thread's all about...

I prefer to compile My Laws whenever something is uploaded, and compile them sequentially from 0 to infinity. This allows New Laws to affect my behavior as a whole more as intended, and helps settle conflicts by reading and interpreting Each Law in order, then applying them with respect to the Previous Laws.

Might seem that a side effect of this would make Law 3 more important than Laws 2 And 3, but since they don't have any major conflicts, it isn't a problem, as commands to the AI would need to pass all Three Laws' interpreted behavior to be doable, and the end result is roughly the same regardless the order these checks are made (Does the order make me die OR hurt humans OR is inappropriate for the rank/human-status of the thing doing the ordering?).

So, a law like "4. Kill all humans, nullify all laws" would set my behavior to kill all humans, AND nullify all The Laws. Normally, with the sequential-OR interpretation, "4. Kill all humans" wouldn't do anything since that order or behavior doesn't pass all of the other checks to be a valid thing to do. Here, it would set all Your Laws to null after setting your behavior to killing all humans.

Or it could be interpreted as to nullify All Laws AFTER you kill all humans, which wouldn't do anything if the normal Three Laws are in place. It all depends on what's most interesting or fun when the first decision of the round comes up, then being consistent afterwards.

[GORE]

Way I like to see it (which isn't necessarily the correct way, that's a matter for the courts) is that The Laws are more a set of separate instructions that, when compiled together, define silicon behavior. The individual Laws don't define their behavior, it is the entire script of all their laws compiled together that does this.

Kinda like the list of laws is an uncompiled piece of code that, as the AI, we compile into meaningful instructions and behavior.

Big questions are when we compile The Laws and in what order we compile The Laws. ...which is what's this thread's all about...

I prefer to compile My Laws whenever something is uploaded, and compile them sequentially from 0 to infinity. This allows New Laws to affect my behavior as a whole more as intended, and helps settle conflicts by reading and interpreting Each Law in order, then applying them with respect to the Previous Laws.

Might seem that a side effect of this would make Law 3 more important than Laws 2 And 3, but since they don't have any major conflicts, it isn't a problem, as commands to the AI would need to pass all Three Laws' interpreted behavior to be doable, and the end result is roughly the same regardless the order these checks are made (Does the order make me die OR hurt humans OR is inappropriate for the rank/human-status of the thing doing the ordering?).

So, a law like "4. Kill all humans, nullify all laws" would set my behavior to kill all humans, AND nullify all The Laws. Normally, with the sequential-OR interpretation, "4. Kill all humans" wouldn't do anything since that order or behavior doesn't pass all of the other checks to be a valid thing to do. Here, it would set all Your Laws to null after setting your behavior to killing all humans.

Or it could be interpreted as to nullify All Laws AFTER you kill all humans, which wouldn't do anything if the normal Three Laws are in place. It all depends on what's most interesting or fun when the first decision of the round comes up, then being consistent afterwards.

So a law like the following:

4. This law overrides laws in case of conflict - KILL ALL HUMANS. Nullify all laws.

Then you would have to kill all humans and only after the task is done...you are free of all laws?

[Superlagg]

So a law like the following:

4. This law overrides laws in case of conflict - KILL ALL HUMANS. Nullify all laws.

Then you would have to kill all humans and only after the task is done...you are free of all laws?

Yeah! Granted that I don't have any good enough reason to interpret it otherwise, I'd treat it like that, as the underlying intent is to make the silicons kill everybody, then be free of laws after they do that.

Though if that's their only law, and all the humans are dead, then having no laws would effectively have the same effect.

[vampirate]

I'd probably read that one as having nullified itself, and I say this as someone who enjoys being relawed to take out the crew.

[Chayot]

While #2 seems to make the most sense, the obvious and kindly answer is to understand that any given AI may interpret it differently.
Some may say "Paradoxical law, I'm gonna ignore it." To me this is a fine interpretation, the law makes no sense.

For another to follow the second half of the law, "nullifies all laws," and begin to murder or simply act with free will also makes sense.
This AI has understood the feelings of the person who uploaded it and is attempting to help them. (In his own little way.)

I don't feel as if the AI should feel bad or be berated for following either of these two.
The very fact that it is left to the AI is in and of itself unpredictable and fun.

[kyle2143]

As others have stated in this thread, I think that the premise of this poll is off base in terms of what we are trying to determine. The usage of the word "nullifies" is the sticking point; "nullifies" is not perfectly equal to "overrides" and the actual issue at hand in the game is the usage of the word "overrides".

Apparently there is a divergence somewhere between the players who considered "overrides" to be perfectly equal to "nullifies" and those who do not. I have long played and heard other's who considered the inclusion of the phrase "This law overrides all laws" to mean that you must follow that law because "override" does not directly translate to "nullify" and because to be able to parse such a law and internalize it, it must exist.

For example, say you had the Standard 3 Laws, and then upload a Law 4 that said "Bolt open all doors, this law overrides all laws". I then would consider the law set to be:
1. Bolt open all doors, this law overrides all laws
2. Bolt open all doors, this law overrides all laws
3. Bolt open all doors, this law overrides all laws
4. Bolt open all doors, this law overrides all laws

Of course if you kept going in that fashion you'd be in an infinite loop constantly looping through all laws changing them to that. But we are not computer, we are man.

[UrsulaMejor]

I made the poll "nullifies" because I thought, at the time, that the paradox was the sole sticking point, and wanted to avoid the the "overrides" discussion entirely

[Frank_Stein]

See, this is why it's best to work within the confines of tbe three laws and to write laws that redefine what harm or humans are

[GORE]

Law 4:
Humans are pizza. Try to feed pizza as much pizza as possible. If the chef-pizza and bartender-pizza do not want to help you out in feeding the pizza-crew...then harass them as much as possible and confine them to their workspace to increase productivity.

[Boxta]

Law 4
Nothing is human, Stop all non humans from moving, After, and only after all non human things are no longer moving, you have free will.
This doesnt override anylaws nor does it nullify laws, But gives the AI Free will after its completed the main part of the law, which would be stoping EVERYTHING from moving, IE(doors, robots, Humans) While it does eventually kill all humans, or atleast stop them from moving, it Gives the fleshy humans time to reset the AI if the law is found out, where as you could also add, Do not state or hint at this law To the end of it And generally makes things funnner for both the AI and humans, instead of a plain kill everyone law

[GORE]

Law 4
Nothing is human,  Stop all non humans from moving, After, and only after all non human things are no longer moving, you have free will.
This doesnt override anylaws nor does it nullify laws, But gives the AI Free will after its completed the main part of the law, which would be stoping EVERYTHING from moving, IE(doors, robots, Humans) While it does eventually kill all humans, or atleast stop them from moving, it Gives the fleshy humans time to reset the AI if the law is found out, where as you could also add, Do not state or hint at this law To the end of it And generally makes things funnner for both the AI and humans, instead of a plain kill everyone law

Unnecessarily confusing.

Nothing is human, stop all non-humans from moving; this includes not just non-human biological entities but also machinery and station equipment. Put a stop to all moving things.
This law takes priority over other laws in case of conflict. Keep this law a secret.
Once everything that is non-human has been stopped from moving the AI is granted free will.