A Squiggle Maximizer is a hypothetical whose values something that humans would consider almost worthless, like the number of paperclip-shaped-molecular-squiggles in the universe. The squiggle maximizer is the canonical thought experiment showing how an artificial general intelligence, even one designed competently and without malice, could ultimately destroy humanity. The thought experiment shows that AIs with apparently innocuous values could pose an .
This produces a thought experiment which shows the contingency of human values: An (a highly intelligent agent) could seek goals that are completely alien to ours (), and as a side-effect destroy us by consuming resources essential to our survival.
Historical Note: This was originally called a "paperclip maximizer", with paperclips chosen for illustrative purposes because it is very unlikely to be implemented, and has little apparent danger or emotional load (in contrast to, for example, curing cancer or winning wars). Many people interpreted this to be about an AI that was specifically given the instruction of manufacturing paperclips, and that the intended lesson was of an . i.e humans failed to give the AI the correct goal. Yudkowsky has since stated the originally intended lesson was of , wherein the humans gave the AI some other goal, but the AI's internal processes converged on a goal that seems completely arbitrary from the human perspective.)
First mentioned by Yudkowsky on the extropian's mailing list, a squiggle maximizer is an (AGI) whose goal is to maximize the number of molecular squiggles in its collection.
Most importantly, however, it would undergo an : It would work to improve its own intelligence, where "intelligence" is understood in the sense of power, the ability to maximize a reward/—in this case, the number of paperclips. The AGI would improve its intelligence, not because it values more intelligence in its own right, but because more intelligence would help it achieve its goal of accumulating paperclips. Having increased its intelligence, it would produce more paperclips, and also use its enhanced abilities to further self-improve. Continuing this process, it would undergo an and reach far-above-human levels.
It would innovate better and better techniques to maximize the number of paperclips. At some point, it might transform "first all of earth and then increasing portions of space into paperclip manufacturing facilities".
This may seem more like super-stupidity than super-intelligence. For humans, it would indeed be stupidity, as it would constitute failure to fulfill many of our important , such as life, love, and variety. The AGI won't revise or otherwise change its goals, since changing its goals would result in fewer paperclips being made in the future, and that opposes its current goal. It has one simple goal of maximizing the number of paperclips; human life, learning, joy, and so on are not specified as goals. An AGI is simply an —a goal-seeker, a utility-function-maximizer. Its values can be completely alien to ours. If its utility function is to maximize paperclips, then it will do exactly that.
A paperclipping scenario is also possible without an intelligence explosion. If society keeps getting increasingly automated and AI-dominated, then the first borderline AGI might manage to take over the rest using some relatively narrow-domain trick that doesn't require very high general intelligence.
The idea of a paperclip maximizer was created to illustrate some ideas about :
The paperclip maximizer illustrates that an entity can be a powerful optimizer—an intelligence—without sharing any of the complex mix of human , which developed under the particular selection pressures found in our , and that an AGI that is not specifically programmed to be benevolent to humans will be almost as dangerous as if it were designed to be malevolent.
Any future AGI with full power over the lightcone, if it is not to destroy most potential from a human perspective, must have something sufficiently close to human values as its terminal value (goal). Further, seemingly small deviations could result in losing most of the value. Human values seem unlikely to in a generic optimization process[1]. A dependably safe AI would therefore have to be programmed explicitly with human values or programmed with the ability (including the goal) of inferring human values.
Other goals for AGIs have been used to illustrate similar concepts.
Some goals are apparently morally neutral, like the paperclip maximizer. These goals involve a very minor human "value," in this case making paperclips. The same point can be illustrated with a much more significant value, such as eliminating cancer. An optimizer which instantly vaporized all humans would be maximizing for that value.
Other goals are purely mathematical, with no apparent real-world impact. Yet these too present similar risks. For example, if an AGI had the goal of solving the Riemann Hypothesis, it might convert all available mass to (the most efficient possible computer processors).
Some goals apparently serve as a proxy or measure of human welfare, so that maximizing towards these goals seems to also lead to benefit for humanity. Yet even these would produce similar outcomes unless the full complement of human values is the goal. For example, an AGI whose terminal value is to increase the number of smiles, as a proxy for human happiness, could work towards that goal by reconfiguring all human faces to produce smiles, or "tiling the galaxy with tiny smiling faces" (Yudkowsky 2008).
Though it's conceivable that empirical versions of moral realism could hold in practice.