Airtight and solid presentation by Joscha Bach @Plinz https://slideslive.com/38909848/consciousness-in-humans-and-other-machines … . Should be a mandatory introduction for anyone exploring AGI.
If your needs are not too specific, an agent will gave to set its own goals to satisfy them.
-
-
Satisfy its goals or my needs? If they are the same, then agent just found an optimal path to an end goal still fixed by me. Wondering if there is a difference b/w systems that formulate goals independent of us vs one that just badly deviate from our set goals due to poor design
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Thinking out loud if the path to system autonomy is the existence of an overarching objective function with mutiple solutions, one which is also the solution to our goals or objective. If system is optimized for that func it has its own goal that may or may not align to ours.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
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.