tag:blogger.com,1999:blog-7418154323659625392011-04-21T21:00:40.762+02:00Thoughts on creating the optimal self-improving artificial intelligence, thus bringing about the singularity.Daivdhttp://www.blogger.com/profile/14328955839644654804noreply@blogger.comBlogger61100tag:blogger.com,1999:blog-741815432365962539.post-85415013193443054872007-12-21T14:04:00.000+01:002007-12-21T16:27:06.252+01:00

After my last post about planning I thought some more on the issue and had something close to an epiphany.When you plan, in the solitaire sense, you need rules governing what moves are legal - transformation rules. If you treat these rules like black boxes, just understanding them by playing around with positions and see how they behave, you can only do so much. An important rule might be usable

Daivdhttp://www.blogger.com/profile/14328955839644654804noreply@blogger.com1tag:blogger.com,1999:blog-741815432365962539.post-82423590375567822132007-12-12T16:49:00.000+01:002007-12-13T11:40:38.523+01:00

I would pay a handsome sum (say $1 million, if I could raise it) for a program that could do the following well-defined, seemingly simple, task.General solitaire solverTake as input a list of rules for a solitaire-like game. The rules are deterministic transformation rules, defining which moves are legal given a certain position. The rules will be given in whatever Turing complete language the

Daivdhttp://www.blogger.com/profile/14328955839644654804noreply@blogger.com0tag:blogger.com,1999:blog-741815432365962539.post-56688751432716639652007-09-07T15:08:00.000+02:002007-09-07T15:08:27.299+02:00

The hardest part for me when thinking about seed AI and optimal optimization, is coming up with a good fitness (IQ) test. Since you need the test to run fast, you end up testing that the algorithm can get somewhere fast, i.e checking only the extreme beginning of a performance curve that ultimately must continue to be good many thousand times longer. What we want to measure is something like the

Daivdhttp://www.blogger.com/profile/14328955839644654804noreply@blogger.com0tag:blogger.com,1999:blog-741815432365962539.post-5590108207494490592007-09-06T17:00:00.000+02:002007-09-06T16:59:55.410+02:00

I once read a short story about the creation of the world's most powerful computer. In essence, each time they tried to turn it on, they had some minor misfortune, a power outage, the maid accidentaly tripped on, and unplugged, the power cord, etc. The highly technical twist in the end was that since we live in a Multiverse, all things that can happen happens in a separate universe. It turns out

Daivdhttp://www.blogger.com/profile/14328955839644654804noreply@blogger.com0tag:blogger.com,1999:blog-741815432365962539.post-5361508942969350602007-09-05T14:50:00.000+02:002007-09-06T12:01:06.409+02:00

The deed is done.I and my friend Nils made a "sprint" last night, where we finished the first version of our seed AI.First we made a simple IQ-function that tests how well a program (a Program Generator or PG) can generate new programs (leaves) from feedback of how close a leaf is to what we want.A PG that receives the best IQ so far gets a chance to generate new PG's, in effect it becomes a

Daivdhttp://www.blogger.com/profile/14328955839644654804noreply@blogger.com0tag:blogger.com,1999:blog-741815432365962539.post-48428677351204158492007-08-30T15:24:00.000+02:002007-09-06T17:00:37.116+02:00

Le grand assumptionThe assumption of seed AI is this: If we can make a program intelligent enough, a "seed" of intelligence, we can also make it gradually improve itself.If intelligence can be expressed as a short formula (think Maxwell's equations or E = mc2), we might not need to make a seed. We will simply have to find that formula. In general, the No-Free-Lunch theorem implies that there must

Daivdhttp://www.blogger.com/profile/14328955839644654804noreply@blogger.com1