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 outer alignment failure. i.e humans failed to give the AI the correct goal. TheYudkowsky has since stated the originally intended lesson was of inner alignment failure, 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 discussed in conversations betweenmentioned by Yudkowsky and Bostrom (circa 2003)on the extropian's mailing list, a squiggle maximizer is an artificial general intelligence (AGI) whose goal is to maximize the number of molecular squiggles in its collection.
A PaperclipSquiggle Maximizer is a hypothetical artificial intelligence whose utility function values something that humans would consider almost worthless, like maximizing the number of paperclipspaperclip-shaped-molecular-squiggles in the universe. The paperclipsquiggle 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 existential threat.
The goal of maximizing paperclips is 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). This produces a thought experiment which shows the contingency of human values: An extremely powerful optimizer (a highly intelligent agent) could seek goals that are completely alien to ours (orthogonality thesis), 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 outer alignment failure. i.e humans failed to give the AI the correct goal. The originally intended lesson was of inner alignment failure, 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 described bydiscussed in conversations between Yudkowsky and Bostrom (2003)(circa 2003), a paperclipsquiggle maximizer is an artificial general intelligence (AGI) whose goal is to maximize the number of paperclipsmolecular squiggles in its collection. If it has been constructed with a roughly human level of general intelligence, the AGI might collect paperclips, earn money to buy paperclips, or begin to manufacture paperclips.
Any future
AGI,AGI with full power over the lightcone, if it is not to destroyus,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 valuesdon'tseem unlikely to spontaneously emerge in a generic optimizationprocess.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.Though it's conceivable that empirical versions of moral realism could hold in practice.