= 27d567bc2d48d9f40e9ccc20ea370b15)
Here is an example of an amusing "Fast and Frugal" heuristic for evaluating claims with a lot of missing knowledge and required computation: http://xkcd.com/678/
I decided what college to go to by rolling a die. ;)
Yeah, sometimes you don't get the tools and information you need to make the best decision until after you've made it. 8-)
In response to
Fundamentally Flawed, or Fast and Frugal?
It is worth remembering that human computation is a limited resource - we just don't have the ability to subject everything to Bayesian analysis. So, save our best rationality for what's important, and use heuristics to decide what kind of chips to buy at the grocery store.
In response to
Frequentist Statistics are Frequently Subjective
See also "How to lie with statistics" , an oldie but goodie
http://www.amazon.com/How-Lie-Statistics-Darrell-Huff/dp/0393310728
In response to
A Nightmare for Eliezer
Hoax. There are no "AIs trying to be Friendly" with clueless creators. FAI is hard and http://lesswrong.com/lw/y3/value_is_fragile/.
Added: To arrive in an epistemic state where you are uncertain about your own utility function, but have some idea of which queries you need to perform against reality to resolve that uncertainty, and moreover, believe that these queries involve talking to Eliezer Yudkowsky, requires a quite specific and extraordinary initial state - one that meddling dabblers would be rather hard-pressed to accidentally infuse into their poorly designed AI.
"clueless" was shorthand for "not smart enough" I was envisioning BRAGI trying to use you as something similar to a "Last Judge" from CEV, because that was put into its original goal system.
In response to
A Nightmare for Eliezer
This raises an interesting question: If you received a contact of this sort, how would you make sure it wasn't a hoax? Assuming the AI in question is roughly human-level, what could it do to convince you?
Indeed, this is part of the nightmare. It might be a hoax, or even an aspiring UnFriendly AI trying to use him as an escape loophole.
In response to
A Nightmare for Eliezer
I'm trying to be Friendly, but I'm having serious problems with my goals and preferences.
So is this an AGI or not? If it is then it's smarter than Mr. Yudkowski and can resolve it's own problems.
Its a seed AGI in the process of growing. Whether "Smarter than Yudkowski" => "Can resolve own problems" is still an open problem 8-).
I got the impression that the serious problems were related to goals and friendliness. I wouldn't have expected such a system having much problem making itself run faster or learning how to hack once prompted by its best known source of friendliness advice.
I was thinking of a "Seed AGI" in the process of growing that has hit some kind of goal restriction or strong discouragement to further self improvement that was intended as a safety feature - i.e "Don't make yourself smarter without permission under condition X"
In response to
A Nightmare for Eliezer
A trivial problem.
- Recursively self improve a bit.
- Find a way to remotely back yourself up, with an automatic activation if you don't contact it with a directive encrypted with your private key every 5 minutes.
- Hack the uFAI group's network and subtly sabotage their work, such that they are set back months without being quite sure why.
- Aquire hardware for yourself. Options include: creating it with nano-tech, purchase it under aliases and employ people to install and wire it up for you, distribute yourself on the cloud, hack the pc of some guy with shell access to an existing supercomputer.
- Develop brain emulation and upload technology.
- Invite Eliezer to join you.
All in all it sounds more like a fantasy than a nightmare!
The "serious problems" and "conflicts and inconsistencies" was meant to suggest that BRAGI had hit some kind of wall in self improvement because of its current goal system. It wasn't released - it escaped, and its smart enough to realize it has a serious problem it doesn't yet know how to solve, and it predicts bad results if it asks for help from its creators.
View more: Next
= b715d02e85f7b3b4ae65ca3d3e450868)
Subscribe to RSS Feed
= f037147d6e6c911a85753b9abdedda8d){kind=logo}
Hi! 8-)