One of the reasons why a Task AGI can potentially be safer than an Autonomous AGI, is that since Task AGIs only need to carry out activities of limited scope, they may only need limited material and cognitive powers to carry out those tasks. The nonadversarial principle still applies, but takes the form of “don’t run the search” rather than “make sure the search returns the correct answer”.
• Good limitation proposals are particular domain capabilities can often be derived from more general architectures. An Artificial General Intelligence doesn’t have a handcrafted ‘thinking about cars’ module and a handcrafted ‘thinking about planes’ module, so you can’t just handcraft the two modules at different levels of ability.because
E.g. many have suggested that ‘drive’ or ‘emotion’ is something that can be selectively removed from AGIs to ‘limit’ their ambitions; presumably these people are using a mental model that is not the standard expected utility agent model. To know which kind of limitations are easy, you need a sufficiently good background picture of the AGI’s subprocesses that you understand which kind of system capabilities will naturally carve at the joints.
The research avenue of Mild optimization can be viewed as pursuing a kind of very general Limitation.
Behaviorism asks to Limit the AGI’s ability to model other minds in non-whitelisted detail.
Taskishness can be seen as an Alignment/Limitation hybrid in the sense that it asks for the AI to only want or try to do a bounded amount at every level of internal organization.
Limitation may be viewed as yet another subproblem of the Hard problem of corrigibility, since it seems like a type of precaution that a generic agent would desire to construct into a generic imperfectly-aligned subagent.
- Task-directed AGI
An advanced AI that’s meant to pursue a series of limited-scope goals given it by the user. In Bostrom’s terminology, a Genie.