Half a croissant, on a plate, with a sign in front of it saying '50c'
h a l f b a k e r y
Number one on the no-fly list

idea: add, search, annotate, link, view, overview, recent, by name, random

meta: news, help, about, links, report a problem

account: browse anonymously, or get an account and write.

user:
pass:
register,


                           

Zigzag Moiré Emojis to Control Marauding Robots

Dazzle Flashcards to distract and mollify robots operating outside of their original behavioral parameters
  (+5)
(+5)
  [vote for,
against]

AI is with us - it reads our words, translates our languages, recognises our faces, plans our journeys, it is beginning to drive our cars.

Some of this is largely performed using great swathes of linear algebra - but more frequently, neural networks, which are coded using even greater swathes of linear algebra - and lots and lots of sample data.

What these things are not coded in, is what people think of as "programming". These systems don't shutdown whenever they're exposed to "The Liar Paradox" because they don't operate according to rules and logic. They are exposed to masses and masses of training data, and learn, through experience, how to recognise, balance and behave.

How do you control such a thing, after you install a battery-pack and let it off by itself?

One method would be to expose a great big red button, surround it in yellow and black wasp-striping with instructions to press firmly "Only in Rare Case of Marauding".

A more subtle approach might be to include, as part of the training data, strong impulses to track, follow and have curiosity in certain specific designs.

These might be geometric patterns rarely seen in "the wild" and unique to each brand of robot manufacturer.

Should an engineer wish to debug a malfunctioning robot, he'd simply open his lever-arch file, flip to the appropriate page, titled in English with "Shutdown", but portraying some zigzag moiré emoji, and hold the image aloft.

Any robots seeing the image would switch their focus to it immediately since all their training data will have included samples from this (and other) command images inserted into their learning data.

The result would be a strong physiological effect jamming up their entire neural system during which time maintenance could be carried out.

zen_tom, Jul 17 2017

Halfbakery: Alcohol Equivalent for AI Alcohol Equivalent for AI
A tangendental idea that got me thinking. [zen_tom, Jul 17 2017]

https://en.wikipedi.../AI_control_problem [Ian Tindale, Jul 17 2017]

[link]






       I think the Big Red Off Button would be more robust.
MaxwellBuchanan, Jul 17 2017
  

       It won't work. It is a known problem.
Ian Tindale, Jul 17 2017
  

       Then the answer is to also have one of those huge levers with the ebonite handle that arcs when you pull the switch.
MaxwellBuchanan, Jul 17 2017
  

       So agreed, big red buttons/ebonite kill-switches are the must-have failsafe, but reaching this switch is difficult under marauding conditions, especially in cases where the robots doing the marauding have been heavily armed or otherwise become 'tricky', hence this additional failsafe.   

       A sensory fascinator, similar to those that we as humans are susceptible to due to our own haphazard wiring and construction patterns leaves room for a suitably informed engineer to make an intervention before it comes to some real-estate damaging robocop face-off type scenario.   

       Furthermore, including such emotional and sensory cues into a robot's data-feed provides seeds for the crystals of future robotic forms of spiritualism and belief to form around - or, as mentioned in an idea elsewhere in this place, for them to potentially mess with to get high (or drunk, depending on your preferred adjective).
zen_tom, Jul 17 2017
  

       In my experience with robots (and that experience is slightly more than you might imagine), they are very easy to disable. For example, failing to place everything exactly where the robot expects to find it will generally disable it, often expensively.
MaxwellBuchanan, Jul 17 2017
  

       Disable a robot? Just remove the battery.
po, Jul 17 2017
  

       By jove I think I got it !   

       25 years ago I wondered about this conundrum as AI was a hobby. I used to think it was going to be solved by meta levels of computing above AI, but of course it can be solved by system voting like that used on Shuttle computers.   

       You can imagine various types of people looking to program their robot with a jury of 12 AI training sets that offer various cost / performance / insurance benefits.   

       But to realise that training sets can me mandated to include a jury of economic factors is a higher order closer to fulfilling Asimov's laws than a raw single factor training set.   

       I thank you.
bigsleep, Jul 17 2017
  

       Maybe hardcode a code word?   

       What if they're programming crashes and they simply continue doing whatever task loop they're caught in, until they do something stupid like drive off a cliff? The halting problem seems like impending catastrophe. No?   

       The really hard thing about AI will be trying to prevent foreign interlopers from using our AI against us. Say we program our cars to do the driving. If there were some shutdown maintenance emoji or a hardcoded maintenance mode word or somesuch, then enemies could shut down our entire grid of AI rather easily.
RayfordSteele, Jul 17 2017
  

       //place everything exactly where the robot expects to find it//   

       //programming crashes and they simply continue doing whatever task loop they're caught in//   

       See, these two types of "robotic" behaviours are suggest what we might consider as being "Type 1" robots - that is, robots whose functioning is traditionally programmed. These robots are hard- coded to operate and can only sensibly function under extremely narrow set of working conditions.   

       Contrast with more modern "Type 2" robots that make decisions not based on programmed logical flows, but instead are taught using vast sets of training data. These robots are capable of machine vision, self-guidance, obstacle avoidance, language translation and a bunch of diverse other things - the thread linking them all together being that they aren't programmed, they are taught.   

       It's these types of complex pattern recognisers that we are yet to construct a set of practical working best-practices. If a computer program fails, you debug it, but if a neural net settles into an unwanted set of behaviours, short of downloading gigabytes of net-weightings and stirring them around a bit, there's not much that can be done, debugging-wise.   

       If instead, we embed control commands into the training process, we get the ability to create debugging-type behaviours, but at a higher level. It's interesting because it suggests instead of debuggers, these type 2 robots are more likely to require a kind of therapy or psychology.   

       The idea posits a robot psychologist using some kind of Rorschach icon to induce a mesmer-like or altered state of operation.   

       Yes, care would have to be taken to reduce possible hacking scenarios, just like with any other technology.
zen_tom, Jul 18 2017
  

       Only one of them would need therapy. The rest could simply download the results.   

       Ooh, there's a book plot in there somewhere. Feels Asimov-like.
RayfordSteele, Jul 18 2017
  

       The displayed zigzag moire emoji to ward off marauding AI reminds me of the use of Elder Symbols against shoggoths.
bungston, Jul 18 2017
  
      
[annotate]
  


 

back: main index

business  computer  culture  fashion  food  halfbakery  home  other  product  public  science  sport  vehicle