AI learns to write its own code by stealing from other programs

Re:AI learns to write its own code by stealing from other pr... by falcolas on Thursday February 23, 2017 @08:44AM (#13713757)

This makes the assumption that every program it writes is somehow guaranteed to be better than the original. Why would it not run into the Multiplicity problem, where each subsequent copy is a bit dumber than the original?

I would think it would be much more likely follow a normal evolutionary model - improve itself to a local maxima, then just stall while the random mutations fail to make the huge leap required to hit the next maxima.

We can't even properly model the human mind in computers yet - not enough processing power - so it follows that an AI which is "better" than humans would require even more processing power than that required to ape humans.

[ Parent | on HN ]

Re:AI learns to write its own code by stealing from other pr... by adangert on Thursday February 23, 2017 @10:15AM (#13714501)

The difference here is the "intelligence" of an AI can be described as a loss function, so if an AI can build and then train another AI which can achieve a better overall score from many examples in its loss function, then that AI, with perhaps a deep neural network will start to "understand" or the components that make a successful neural network. Thus it could use intelligence rather than random mutations to evolve.

[ Parent | on HN ]