Open Thread: March 4 - 10

Scott Garrabrant

If it's worth saying, but not worth its own post (even in Discussion), then it goes here.

Hi, long time lurker, new user. I was thinking about writing a post on how any potential AGI of human-level intelligence is likely to have a band of a few years before and after its creation where FOOM risks can be contained with care, and how this would be an especially fruitful period to deal with friendliness. Any posts/articles I should look at to avoid being too redundant?

Intelligence Explosion Microeconomics discusses the kinds of open questions we'd need to answer in order to know whether or not there will be such a band.

Section 2.3. (and its subsections) of Responses to Catastrophic AGI Risk also discusses three different types of FOOM that might be possible: hardware overhang, speed explosion, and an intelligence explosion. Your argument should probably address all three.

1Strilanc12y

There's a post somewhere about two entities discussing how evolution is optimizing so quickly, compared to how things were before. One of them tries to argue that brains will be even faster while the other scoffs that brains making machines with hundreds of moving parts in as little as a thousand years is absurd. Of course it's an allegory for the next jump also having a massive time scale difference, with things that used to take years taking only minutes. Unfortunately I can't find the post and I can't remember what it's called.

2Strilanc12y

You should read Eliezer's post That Alien Message. [...]

7

Open Thread: March 4 - 10

7

If it's worth saying, but not worth its own post (even in Discussion), then it goes here.

7

7

Open Thread: March 4 - 10

7

If it's worth saying, but not worth its own post (even in Discussion), then it goes here.

7