[agi] HumesGuillotine

2023-07-08 Thread James Bowery
HumesGuillotine This repository is a series of competitions toward rigorous ethics in AGI founded on Hume's Guillotine : Separating the question of what *IS* from what *OUGHT* to be the case. Artificial Genera

Re: [agi] Re: deepmind-co-founder-suggests-new-turing-test-ai-chatbots-report-2023-6

2023-07-08 Thread James Bowery
But you do use a model of your environment to predict how your friend will react. You *embody* that model as *learned. *The* learning algorithm* involves encoding the knowledge in your personal (neurons) and phylogenetic (DNA) *history of experience*. We already have examples of combinations of

Re: [agi] Re: deepmind-co-founder-suggests-new-turing-test-ai-chatbots-report-2023-6

2023-07-08 Thread WriterOfMinds
When I see the word "science," I think of something more specific than the ability to predict the outcomes of actions. I don't use the formal scientific method to determine how a friend will react to a particular gift, for example. -- Artificial General Int

Re: [agi] Re: deepmind-co-founder-suggests-new-turing-test-ai-chatbots-report-2023-6

2023-07-08 Thread James Bowery
One needs to define the ability to predict consequences of various actions in order to program an AGI. If you don't want to call that "science" that's fine. I don't care what you call it. But Ron Freeman certainly takes that as attempting to "define science". On Sat, Jul 8, 2023 at 8:42 AM Matt

Re: [agi] deepmind-co-founder-suggests-new-turing-test-ai-chatbots-report-2023-6

2023-07-08 Thread James Bowery
The Suleyman Test -- an agent outcompeting humans for money -- reveals Suleyman's insight into the unfriendly AGI known in the vernacular as "The Global Economy" which is a "Money Maximizer" as opposed to a "Paperclip Maximizer". But he still elides the foundation of intelligence in creating a pre

Re: [agi] Re: deepmind-co-founder-suggests-new-turing-test-ai-chatbots-report-2023-6

2023-07-08 Thread Matt Mahoney
You don't need to define science. Occam's Razor works as the basis for choosing theories in all branches of science because all possible probability distributions over the countably infinite set of strings must favor shorter strings. -- Artificial General In