The feedback given by humans to align artificial intelligence is limited by the reaction time and processing speed of the finite number of us, now less than $2^{33}$. As an artificial intelligence (or a growing number of them) grows in complexity, more and more possible actions need to be checked for human compatibility. But human feedback cannot grow at the pace of that expanding machine, therefore necessarily weakening the coupling between natural and artificial intelligence.

Does this make alignment impossible in practice?

  • $\begingroup$ A narrow model aligns the bigger model? $\endgroup$
    – Vepir
    Apr 8, 2023 at 23:12
  • $\begingroup$ Then the bigger model cannot develop the ability to perform any new action whose fitness is not evaluated beforehand. $\endgroup$ Apr 9, 2023 at 3:15
  • 1
    $\begingroup$ In other words, our values exist -if at all- with respect to current options. We do not have preferences yet for future situations made possible by future systems. And the speed of appearance of those new scenarios will be faster than our speed for providing any meaningful feedback. $\endgroup$ Apr 9, 2023 at 3:19
  • 1
    $\begingroup$ In particular, are we ready for AI to beat us at the language game too, after having been surpassed at chess and go? $\endgroup$ Apr 9, 2023 at 3:29
  • $\begingroup$ Indeed it has the potential to have intelligence explosion out of control by original design, thus it needs to have some strict formal proof for the safety of self-growth or modification (like a self-replicated cellular automaton in Conway's Games of Life) limiting any bad effect, ad hoc engineering is perhaps dangerous here. $\endgroup$
    – cinch
    Apr 10, 2023 at 5:16


You must log in to answer this question.

Browse other questions tagged .