It would be a lot easier if the global population stabilized at around 1 billion. It's conceivable we could get down to that by bringing 3rd world areas up to 1st world standards in terms of women's rights, access to birth control, education, standard of living, etc., since developed nations have had declining birth rates for quite a while. But it's not a cheap or popular idea & would take several generations anyway.
A lot of things would be easier if 90% of people suddenly disappeared, but there is absolutely no sane scenario in which we actively chase such an unbelievably low population count.
The birth rates are declining in large part because of the expenses and time required to raise a kid these days. If life was perfectly easy for anyone to have a child, then the population increases. So, what - you’re going to kill extra children? Forcibly sterilize most? Purposely make life difficult so people lose interest?
I didn't propose any of those things you mentioned & am strongly opposed to them. If I were proposing anything, it would be more along the lines of ending theocracies, increasing equality, access to education, birth control & abortion services, & creating a social safety net so people don't have to rely on having as many kids as possible to assist in subsistence farming. But like I said, none of this is a popular goal - especially not among billionaires or the global south - so my comment was more of an idle musing than anything resembling a proposal.
I know you didn't propose those things - I'm saying they are going to be required in order to force the population to stay at an unreasonably low 1 billion people on Earth forever
I'm doing the same since this is the only method I found I can let my bot access the files, something I couldn't achieve with Obsidian Sync.. until now!
How is remotely save obsidian plugin mentioned only once here? I set it up with a OneDrive I was already using anyway to host and sync my vault there. I have it set up and synced on 4 devices with 4 different os (win11, macos, ios, android) and it works great and is free.
This is why tutorials in programming don't really teach much because you get the finished version. Not all the wrong steps that were taken, why they failed, what else was tried.
These steps are what help you solve other issues in the future.
Make (or whatever) targets that direct output to file and returns a subset have helped me quite a bit. Then wrap that in an agent that also knows how and when to return cached and filtered data from the output vs. rerunning. Fewer tokens spent reading output details that usually won't matter, coupled with less context pollution in the main agent from figuring out what to do.
If you use a smaller model for the sub agent you get all three
Of course you can combine both approaches for even greater gains. But Claude Code and like five alternatives gaining an efficient tool-calling paradigm where console output is interpreted by Haiku instead of Opus seems like a much quicker win than adding an LLM env flag to every cli tool under the sun
Dunno about that. Having used the $20 claude plan, I ran out of tokens within 30 minutes if running 3-4 agents at the same time. Often times, all 3-4 will run a build command at the end to confirm that the changes are successful. Thus the loss of tokens quickly gets out of hand.
Edit: Just remembered that sometimes, I see claude running the build step in two terminals, side-by-side at nearly the same time :D
reply