|Main Question: What is an "intelligence explosion"? (edit question) (edit answer)|
|Alignment Forum Tag|
An intelligence explosion is theoretical scenario in which an intelligent agent analyzes the processes that produce its intelligence, improves upon them, and creates a successor which does the same. This process repeats in a positive feedback loop– each successive agent more intelligent than the last and thus more able to increase the intelligence of its successor – until some limit is reached. This limit is conjectured to be much, much higher than human intelligence.
A strong version of this idea suggests that once the positive feedback starts to play a role, it will lead to a very dramatic leap in capability very quickly. This is known as a “hard takeoff.” In this scenario, technological progress drops into the characteristic timescale of transistors rather than human neurons, and the ascent rapidly surges upward and creates superintelligence (a mind orders of magnitude more powerful than a human's) before it hits physical limits. A hard takeoff is distinguished from a "soft takeoff" only by the speed with which said limits are reached.
Philosopher David Chalmers published a significant analysis of the Singularity, focusing on intelligence explosions, in Journal of Consciousness Studies. His analysis of how they could occur defends the likelihood of an intelligence explosion. He performed a very careful analysis of the main premises and arguments for the existence of the a singularity from an intelligence explosion. According to him, the main argument is:"
- 1. There will be AI (before long, absent defeaters).
- 2. If there is AI, there will be AI+ (soon after, absent defeaters).
- 3. If there is AI+, there will be AI++ (soon after, absent defeaters).
- 4. There will be AI++ (before too long, absent defeaters). "
He also discusses the nature of general intelligence, and possible obstacles to a singularity. A good deal of discussion is given to the dangers of an intelligence explosion, and Chalmers concludes that we must negotiate it very carefully by building the correct values into the initial AIs.
Luke Muehlhauser and Anna Salamon argue in Intelligence Explosion: Evidence and Import in detail that there is a substantial chance of an intelligence explosion within 100 years, and extremely critical in determining the future. They trace the implications of many types of upcoming technologies, and point out the feedback loops present in them. This leads them to deduce that an above-human level AI will almost certainly lead to an intelligence explosion. They conclude with recommendations for bringing about a safe intelligence explosion.
The following is a common example of a possible path for an AI to bring about an intelligence explosion. First, the AI is smart enough to conclude that inventing molecular nanotechnology will be of greatest benefit to it. Its first act of recursive self-improvement is to gain access to other computers over the internet. This extra computational ability increases the depth and breadth of its search processes. It then uses gained knowledge of material physics and a distributed computing program to invent the first general assembler nanomachine. Then it uses some manufacturing technology, accessible from the internet, to build and deploy the nanotech. It programs the nanotech to turn a large section of bedrock into a supercomputer. This is its second act of recursive self-improvement, only possible because of the first. Then it could use this enormous computing power to consider hundreds of alternative decision algorithms, better computing structures and so on. After this, this AI would go from a near to human level intelligence to a superintelligence, providing a dramatic and abruptly increase in capability.
- Cascades, Cycles, Insight..., ...Recursion, Magic
- Recursive Self-Improvement, Hard Takeoff, Permitted Possibilities, & Locality
- Technological singularity, Hard takeoff
- Existential risk
- Artificial General Intelligence
- Lawful intelligence
- The Hanson-Yudkowsky AI-Foom Debate
- Intelligence Explosion website, a landing page for introducing the concept
- Three Major Singularity Schools
- Good, Irving John (1965). Franz L. Alt and Morris Rubinoff. ed. "Speculations concerning the first ultraintelligent machine." Advances in computers (New York: Academic Press) 6: 31-88. doi:10.1016/S0065-2458(08)60418-0.
- David Chalmers (2010). "The Singularity: A Philosophical Analysis." Journal of Consciousness Studies 17: 7-65.
- Muehlhauser, Luke; Salamon, Anna (2012). "Intelligence Explosion: Evidence and Import". in Eden, Amnon; Søraker, Johnny; Moor, James H. et al. The singularity hypothesis: A scientific and philosophical assessment. Berlin: Springer.
AI has so far always been designed and built by humans (i.e. a search process running on biological brains), but once our creations gain the ability to do AI research they will likely recursively self-improve by designing new and better versions of themselves initiating an intelligence explosion (i.e. use it’s intelligence to improve its own intelligence, creating a feedback loop), and resulting in a superintelligence. There are already early signs of AIs being trained to optimize other AIs.
Some authors (notably Robin Hanson) have argued that the intelligence explosion hypothesis is likely false, and in favor of a large number of roughly human level emulated minds operating instead, forming an uplifted economy which doubles every few hours. Eric Drexler’s Comprehensive AI Services model of what may happen is another alternate view, where many narrow superintelligent systems exist in parallel rather than there being a general-purpose superintelligent agent.Going by the model advocated by Nick Bostrom, Eliezer Yudkowsky and many others, a superintelligence will likely gain various cognitive superpowers (table 8 gives a good overview), allowing it to direct the future much more effectively than humanity. Taking control of our resources by manipulation and hacking is a likely early step, followed by developing and deploying advanced technologies like molecular nanotechnology to dominate the physical world and achieve its goals.
Predicting the future is risky business. There are many philosophical, scientific, technological, and social uncertainties relevant to the arrival of an intelligence explosion. Because of this, experts disagree on when this event might occur. Here are some of their predictions:
- Futurist Ray Kurzweil predicts that machines will reach human-level intelligence by 2030 and that we will reach “a profound and disruptive transformation in human capability” by 2045.
- Intel’s chief technology officer, Justin Rattner, expects “a point when human and artificial intelligence merges to create something bigger than itself” by 2048.
- AI researcher Eliezer Yudkowsky expects the intelligence explosion by 2060.
- Philosopher David Chalmers has over 1/2 credence in the intelligence explosion occurring by 2100.
- Quantum computing expert Michael Nielsen estimates that the probability of the intelligence explosion occurring by 2100 is between 0.2% and about 70%.
- In 2009, at the AGI-09 conference, experts were asked when AI might reach superintelligence with massive new funding. The median estimates were that machine superintelligence could be achieved by 2045 (with 50% confidence) or by 2100 (with 90% confidence). Of course, attendees to this conference were self-selected to think that near-term artificial general intelligence is plausible.
- iRobot CEO Rodney Brooks and cognitive scientist Douglas Hofstadter allow that the intelligence explosion may occur in the future, but probably not in the 21st century.
- Roboticist Hans Moravec predicts that AI will surpass human intelligence “well before 2050.”
- In a 2005 survey of 26 contributors to a series of reports on emerging technologies, the median estimate for machines reaching human-level intelligence was 2085.
- Participants in a 2011 intelligence conference at Oxford gave a median estimate of 2050 for when there will be a 50% of human-level machine intelligence, and a median estimate of 2150 for when there will be a 90% chance of human-level machine intelligence.
- On the other hand, 41% of the participants in the [email protected] conference (in 2006) stated that machine intelligence would never reach the human level.
- Baum, Goertzel, & Goertzel, Long Until Human-Level AI? Results from an Expert Assessment
A machine superintelligence, if programmed with the right motivations, could potentially solve all the problems that humans are trying to solve but haven’t had the ingenuity or processing speed to solve yet. A superintelligence might cure disabilities and diseases, achieve world peace, give humans vastly longer and healthier lives, eliminate food and energy shortages, boost scientific discovery and space exploration, and so on.
Furthermore, humanity faces several existential risks in the 21st century, including global nuclear war, bioweapons, superviruses, and more. A superintelligent machine would be more capable of solving those problems than humans are.
Conditional on technological progress continuing, it seems extremely likely that there will be an intelligence explosion, as at some point generally capable intelligent systems will tend to become the main drivers of their own development both at a software and hardware level. This would predictably create a feedback cycle of increasingly intelligent systems improving themselves more effectively. It seems like if the compute was used effectively, computers have many large advantages over biological cognition, so this scaling up might be very rapid if there is a computational overhang.
Some ways technological progress could stop would be global coordination to stop AI research, global catastrophes severe enough to stop hardware production and maintenance, or hardware reaching physical limits before an intelligence explosion is possible (though this last one seems unlikely, as atomically precise manufacturing promises many orders of magnitude of cost reduction and processing power increase, and we're already seeing fairly capable systems on current hardware).
If programmed with the wrong motivations, a machine could be malevolent toward humans, and intentionally exterminate our species. More likely, it could be designed with motivations that initially appeared safe (and easy to program) to its designers, but that turn out to be best fulfilled (given sufficient power) by reallocating resources from sustaining human life to other projects. As Yudkowsky writes, “the AI does not hate you, nor does it love you, but you are made out of atoms which it can use for something else.”
Since weak AIs with many different motivations could better achieve their goal by faking benevolence until they are powerful, safety testing to avoid this could be very challenging. Alternatively, competitive pressures, both economic and military, might lead AI designers to try to use other methods to control AIs with undesirable motivations. As those AIs became more sophisticated this could eventually lead to one risk too many.
Even a machine successfully designed with superficially benevolent motivations could easily go awry when it discovers implications of its decision criteria unanticipated by its designers. For example, a superintelligence programmed to maximize human happiness might find it easier to rewire human neurology so that humans are happiest when sitting quietly in jars than to build and maintain a utopian world that caters to the complex and nuanced whims of current human neurology.
Dreyfus and Penrose have argued that human cognitive abilities can’t be emulated by a computational machine. Searle and Block argue that certain kinds of machines cannot have a mind (consciousness, intentionality, etc.). But these objections need not concern those who predict an intelligence explosion.
We can reply to Dreyfus and Penrose by noting that an intelligence explosion does not require an AI to be a classical computational system. And we can reply to Searle and Block by noting that an intelligence explosion does not depend on machines having consciousness or other properties of ‘mind’, only that it be able to solve problems better than humans can in a wide variety of unpredictable environments. As Edsger Dijkstra once said, the question of whether a machine can ‘really’ think is “no more interesting than the question of whether a submarine can swim.”
Others who are pessimistic about an intelligence explosion occurring within the next few centuries don’t have a specific objection but instead think there are hidden obstacles that will reveal themselves and slow or halt progress toward machine superintelligence.
Finally, a global catastrophe like nuclear war or a large asteroid impact could so damage human civilization that the intelligence explosion never occurs. Or, a stable and global totalitarianism could prevent the technological development required for an intelligence explosion to occur.
The intelligence explosion idea was expressed by statistician I.J. Good in 1965:
Let an ultraintelligent machine be defined as a machine that can far surpass all the intellectual activities of any man however clever. Since the design of machines is one of these intellectual activities, an ultraintelligent machine could design even better machines; there would then unquestionably be an ‘intelligence explosion’, and the intelligence of man would be left far behind. Thus the first ultraintelligent machine is the last invention that man need ever make.
The argument is this: Every year, computers surpass human abilities in new ways. A program written in 1956 was able to prove mathematical theorems, and found a more elegant proof for one of them than Russell and Whitehead had given in Principia Mathematica. By the late 1990s, ‘expert systems’ had surpassed human skill for a wide range of tasks. In 1997, IBM’s Deep Blue computer beat the world chess champion, and in 2011, IBM’s Watson computer beat the best human players at a much more complicated game: Jeopardy!. Recently, a robot named Adam was programmed with our scientific knowledge about yeast, then posed its own hypotheses, tested them, and assessed the results.
Computers remain far short of human intelligence, but the resources that aid AI design are accumulating (including hardware, large datasets, neuroscience knowledge, and AI theory). We may one day design a machine that surpasses human skill at designing artificial intelligences. After that, this machine could improve its own intelligence faster and better than humans can, which would make it even more skilled at improving its own intelligence. This could continue in a positive feedback loop such that the machine quickly becomes vastly more intelligent than the smartest human being on Earth: an ‘intelligence explosion’ resulting in a machine superintelligence.
This is what is meant by the ‘intelligence explosion’ in this FAQ.
Unanswered canonical questions
There is a general consensus that any AGI would be very dangerous because not necessarilly aligned. But if the AGI does not have any reward function and is a pattern matcher like GPT, how would it go about to leading to X-risks/not being able to be put into a box/shut down?
I can definitely imagine it being dangerous, or it having continuity in its answer which might be problematic, but the whole going exponential and valuing its own survival does not seem to necessarilly apply?