JamesAndrix

Comments

On saving the world

Anecdote: I think I've had better responses summarizing LW articles in a few paragraphs without linking, than linking to them with short explanations.

It does take a lot to crosss those inferential distances, but I don't think quite that much.

To be fair, my discussions may not cover a whole sequence, I have the opportunity to pick out what is needed in a particular instance.

Evaluating the feasibility of SI's plan

One trouble is that that is essentailly tacking mind enslavement on to the WBE proposition. Nobody wants that. Uploads wouldn't volunteer. Even if a customer paid enough of a premium for an employee with loyalty modifications, that only rolls us back to relying on the good intent of the customer.

This comes down to the exact same arms race between friendly and 'just do it' . With extra ethical and reverse-engineering hurdles. (I think we're pretty much stuck with testing and filtering based on behavior. And some modification will only be testable after uploading is available)

Mind you I'm not saying don't do work on this, I'm saying not much work will be done on it.

Evaluating the feasibility of SI's plan

I think we're going to get WBE's before AGI.

If we viewed this as a form of heuristic AI, it follows from your argument that we should look for ways to ensure friendliness of WBE's. (Ignoring the ethical issues here.)

Now, maye this is becasue most real approaches would consider ethical issues, but it seems like figuring out how to modify a human brain so that it doesn't act against your interests even if is powerful and without hampering its intellect, is a big 'intractable' problem.

I suspect no one is working on it and no one is going to, even though we have working models of these intellects today. A new design might be easier to work with, but it will still be a lot harder than it wil seem to be worth - as long as the AI's are doing near human level work.

Aim for an AI design that's easy enough to work on saftey that people actually will work on safety... and it will start to look a lot like SIAI ideas.

Harry Potter and the Methods of Rationality discussion thread, part 17, chapter 86

There is some time resolution.

Albus said heavily, "A person who looked like Madam McJorgenson told us that a single Legilimens had lightly touched Miss Granger's mind some months ago. That is from January, Harry, when I communicated with Miss Granger about the matter of a certain Dementor. That was expected; but what I did not expect was the rest of what Sophie found."

Reply to Holden on 'Tool AI'

"When a distinguished but elderly scientist states that something is possible, he is almost certainly right. When he states that something is impossible, he is very probably wrong."

http://en.wikipedia.org/wiki/Clarke%27s_three_laws

[draft] Concepts are Difficult, and Unfriendliness is the Default: A Scary Idea Summary

That would make (human[s] + predictor) in to an optimization process that was powerful beyond the human[s]'s ability to steer. You might see a nice looking prediction, but you won't understand the value of the details, or the value of the means used to achieve it. (Which would be called trade-offs in a goal directed mind, but nothing weighs them here.)

It also won't be reliable to look for models in which you are predicted to not hit the Emergency Regret Button As that may just find models in which your regret evaluator is modified.

Harry Potter and the Methods of Rationality discussion thread, part 10

For example, a hat and a cloak may be a uniform in a secret society, to be worn in special circumstances.

I much like the idea of this being a standard spell, as that provides further cover for your identity.

They Guy Fawkes mask is the modern equivalent.

Load More