It's very unclear what the book emoji is and how to improve it's rate of increase.
It's the total accumulated knowledge, I think.
AGI Simulator
11–20 of 35 posts
Re: AGI Simulator
#12Is there a programmatic way to optimize speedruns for this kind of games? The number of steps/the size of the search space seems too large to apply a MILP solver to it
Re: AGI Simulator
#13Started by maxing AI.
Got hit by the virus.
Maxed alignment after that.
Now in 2066 and waiting for BrainLink
Re: AGI Simulator
#14Whoever made this, please add a "cursor: pointer" to clickable elements pretty please.
and maybe "user-select: none"? Also the "Buy Cloud Service" clickable makes the left column shift in size.
Re: AGI Simulator
#15If you haven't yet also have a look at the old singularity endgame game: https://libregamewiki.org/Endgame:_Singularity it's a bit old and the android port doesn't work anymore, but it's pygame and shouldn't be a problem for the hn crowd to get it going.
Re: AGI Simulator
#16Tangentially related:
I make "AI Simulator" games, where you use AI to run simulations of games automatically.
Re: AGI Simulator
#17Is there a programmatic way to optimize speedruns for this kind of games? The number of steps/the size of the search space seems too large to apply a MILP solver to it
monte carlo or some kind of ant colony simulation probably
Re: AGI Simulator
#18I got the "Universal Jump Engine" and the game reset.
Re: AGI Simulator
#19It seems like AI Knowledge Production and AI Wealth Production are permanently stuck at 0 since they start at 0 and the only modifiers are +X%. Maybe I'm wrong and I just wasted the +X% modifiers by spending them too early?
I believe both are a function of the number of GPUs owned. Did you buy GPUs?
I also didn't see those as press-able buttons until I was pretty deep into the game. UX could use some work :-)
Re: AGI Simulator
#20My first run: I deliberately buy every option that hurts alignment with the goal of killing humanity. Eventually I run out of alignment-harming stuff to buy, and everything else helps so much that around 2080 I have a human population of 14 million.
Second run ('cause I clicked the universal jump engine by accident): I deliberately hold off on AI upgrades unless I can keep alignment high. At 2080, AI is out-earning humanity but very stupid and humanity is only at 586 million.
(Also, why does the population start off so low? Do you know something that I don't?)
EDIT: I bought all the alignment upgrades on the second run. I don't entirely understand how threatening to nuke countries that research AI improves alignment when I'm already running GPT-5 on millions of GPUs