I’m sure there are some AI peeps here. Neural networks scale with size because the number of combinations of parameter values that work for a given task scales exponentially (or, even better, factorially if that’s a word???) with the network size. How can such a network be properly aligned when even humans, the most advanced natural neural nets, are not aligned? What can we realistically hope for?

Here’s what I mean by alignment:

  • Ability to specify a loss function that humanity wants
  • Some strict or statistical guarantees on the deviation from that loss function as well as potentially unaccounted side effects
  • @Thurkeau
    link
    11 year ago

    Clearly you have not seen my character sheet. People tend to be anything from Lawful Good to Chaotic Evil, so that might be something good to check.