Re: Suggested AI-Box protocol & AI-Honeypots

From: James Higgins (
Date: Tue Jul 16 2002 - 02:25:04 MDT

Cliff Stabbert wrote:
> Saturday, July 7, 2001, 4:38:59 PM, Michael Warnock wrote:
> One possible approach to making the AI more amenable to study,
> analysis and containment would be to simply (presuming non-modifiable
> hardware and a very limited communication channel) bring the
> clockspeed down.

> Without external referents, the AI can have no concept or perception
> of time other than number of clock cycles. We can run it at 10GHz or
> 1Hz and it will have no idea unless we clue it in. Fixing our vt100
> transmission speed relative to its clockspeed, e.g. 1 character for
> every 1000 of its clocks, would eliminate at least that clue.

Yes, this would be helpful. It *might* still be possible for the AI to
detect such a situation if it were not very, very carefully done though.
  For example, given much longer to reply a human would be likely to use
better grammar and have better spelling (since they could correct
themselves). Other, more subtle, clues may also be present in Human/AI

> For instance, we *might*, based on how we seeded the AI and how ve grew,
> have reason to think that this chunk of nodes correlates more strongly
> to social/psychological analysis/cognition, and that chunk of nodes
> more strongly to spatial/mathematical cognition, etc.

> > Bringing the clockspeed down -- way down -- during an AI box
> experiment would then let us then study such activation patterns at
> our leisure, and speculate as to what was going on, without the AI
> being able to deduce from an increased latency of our replies that we
> were doing so.

The hardware design could use something like VRAM instead of normal RAM
and be configured so that it could be read by another computer without
affecting the AI's hardware. Combined with a slow clock speed you could
actually record every detail of the AI's processing for detailed analysis.

> Just to clarify: I am in no way arguing that speeding us up relative
> to a transhuman AI could make us "just as intelligent", or that if I
> could just run my brain at 10x the clock speed of yours, that would
> make me 10x as smart -- but I *am* arguing for *some* relative
> improvement, which we can try to maximize by getting the timing right.

But if you could run your brain at 1000x the speed of another person
that might make you equivelant to 10x as smart. No guarantee either way
- we simply don't have the data to know. But being able to
intelligently try 1000 possible solutions before picking one should
greatly improve your intelligence, as percieved by the other party.

James Higgins

This archive was generated by hypermail 2.1.5 : Wed Jul 17 2013 - 04:00:40 MDT