Re: large search spaces don't mean magic

From: Daniel Radetsky (
Date: Tue Aug 02 2005 - 20:25:33 MDT

On Tue, 2 Aug 2005 21:34:16 -0400
Randall Randall <> wrote:

> This is not entirely accurate. Exploits are shorthand for
> "things we didn't think of or protect against, which could
> be used to escape from containment". Psychological tricks
> are one kind of possible exploit, but are a very mundane
> example of them, and hence likely to lull us with the idea
> that we can protect against exploits in general.

That was not how I was using the term. I think it's useful to distinguish
between sweet-talking and box-exploits, and I also think that those exaust the
possibilities for escaping from a box.

> I *believe* that Eliezer's point is merely that anything
> you don't think of or don't protect against can ruin your
> day, not that there is a necessarily a specific physical
> loophole.

Remember, 'cans' are not the issues; the problem is with 'might-very-wells.'

> In any case, the general thing to take away, in my opinion,
> is that since anything you don't think of might in principle
> result in failure to contain, plugging any number of specific
> leaks or classes thereof is not going to reduce the potential
> problem space

Who cares about the "potential problem space"? Unless you are sneaking some
amount of "likely" into "potential," you're just continuing to ignore my point.


This archive was generated by hypermail 2.1.5 : Wed Jul 17 2013 - 04:00:51 MDT