Stop using 'wireheading' and 'reward hacking' interchangeably. They are separate concepts. Wireheading negatively affects the achievement of YOUR goals. Reward hacking negatively affects the achievement of your CREATOR'S goals.
i'm trying to understand this better. in what sense are they your goals if you're not pursuing them and they're not your creator's goals?
-
-
i think you think i said "wireheading involves not pursuing your goals" i said "negatively affects the achievement of your goals" pursuing your goals poorly. we have limited mental resources, a faulty model of the world, impulses calibrated for a way different environment
-
i'm not sure why you're confused about reward hacking? it's not uncommon https://docs.google.com/spreadsheets/d/e/2PACX-1vRPiprOaC3HsCf5Tuum8bRfzYUiKLRqJmbOoC-32JorNdfyTiRRsR7Ea5eWtvsWzuxo8bjOxCG84dAg/pubhtml …
End of conversation
New conversation -
-
-
are they your goals because you're pursuing them in most contexts, just not in the wireheading context?
-
i guess "your creator's goals" and "the thing that your creators intended to be your goals" are also different
-
can be different, i mean. even though there's pressures for them to be the same
End of conversation
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.