During the LessWrong 1.0 Wiki Import we (the LessWrong team) discovered a number of great articles that most of the LessWrong team hadn't read before. Since we expect many others to also not have have read these, we are creating a series of the best posts from the Wiki to help give those hidden gems some more time to shine.
The original wiki article was fully written by Kaj Sotala, who I've added as a coauthor to this post. Thank you for your work on the wiki!
AI advantages are various factors that might favor AIs in case there was ever a conflict between them and humans. These can be classified as hardware advantages, self-improvement capabilities, co-operative advantages, and human handicaps.
- Superior processing power: Having more serial processing power would let an AI think faster than humans, while having more parallel processing power and more memory would let it think about more things at once.
An AI with access to its source code may directly modify the way it thinks, or create a modified version of itself. An AI can intentionally be built in a manner that is easy to understand and modify, and may even read its own design documents. Self-improvement capabilities may enable recursive self-improvement to occur, thereby triggering an intelligence explosion.
- Improving algorithms: An AI may modify its existing algorithms, e.g. making them faster, to consume less memory, or to rely on fewer assumptions.
- Designing new mental modules: A mental module is a part of a mind that specializes in processing a certain kind of information. An AI could create entirely new kinds of modules, custom-tailored for specific problems.
- Modifiable motivation systems: Humans frequently suffer from problems such as procrastination, boredom, mental fatigue, and burnout. A mind which did not become bored or tired with its work would have a clear advantage over humans.
- Copyability: A digital mind can be copied very quickly, and doing so has no cost other than access to the hardware required to run it.
- Perfect co-operation: Minds might be constructed to lack any self-interest. Such entities minds could share the same goal system and co-operate perfectly with one another.
- Superior communication: AIs could communicate with each other at much higher bandwidths than humans, and modify themselves to understand each other better.
- Transfer of skills: To the extent that skills can be modularized, digital minds could create self-contained skill modules to be shared with others.
Humans frequently reason in biased ways. AIs might be built to avoid such biases.
- Biases from computational limitations or false assumptions: Some human biases can be seen as assumptions or heuristics that fail to reason correctly in a modern environment, or as satisficing algorithms that do the best possible job given human computational resources.
- Human-centric biases: People tend to think of the capabilities of non-human minds, such as God or an artificial intelligence, as if the minds in question were human. This tendency persists even if humans are explicitly instructed to act otherwise.
- Biases from socially motivated cognition: It has also been proposed that humans have evolved to acquire beliefs which are socially beneficial, even if those beliefs weren't true.
- Kaj Sotala (2012): Advantages of Artificial Intelligences, Uploads, and Digital Minds. International Journal of Machine Consciousness 4 (1), 275-291.