great approach. I did that with my opencode based setup as well, it's neat and fun to tune skills and mcp loaders and stuff. Then i got fed up with opencode's design limitations. And then, my own harness work is on hold in favor of a harness-puppeteer paradigm, but that one has also been on hold! I'm mostly currently pulling on the thread of making it easier just to review the voluminous conversation turns!
So often we will burn 20% of limit in a single ill conceived agent tool call that we're simply not going to be able to or want to be able to intercept. Where I see a tool like this being a real step forward is to add a decision point. it does not have to bubble up to hard-require user to provide permission, but it can let the LLM have an intermediate checkpoint to say that it's about to get blasted with 30k tokens and here is roughly the shape of it and do you wanna adjust or whittle it down if you know what you're looking for etc.?
There is definitely tons of value to extract from this line of thinking.
I think you might be vastly overcomplicating it because I didn't think there had to be any sort of "conservation of branching" in the MWI. each nondeterministic event (of which unfathomable quantities take place every moment) generates an infinite number of branches so to even conceive of the total geometry of all the branching (e.g. all that could ever take place, truly) is a bit of a mindfuck, and that's probably okay and the way it was intended. It's supposed to be comforting to know that regardless of how bad reality seems, if we could navigate arbitrarily through the branching space/time/universes then there would be unimaginable infinities of joyful utopias to visit.
could you elaborate slightly on what is meant by ancestor simulation? My best stab is that you're saying we're the unknowing entities that they created for fun to get to meet or observe their own ancestors? This still seems far fetched.
The advanced hyperintelligence that descends from us wants to learn about its past, build an interesting tech demo, or perhaps experience it. It creates an advanced simulation of the past using its unimaginable technology. It's able to recreate the past and populate it with realistic people with such fidelity that the simulated people have no idea that they're in a simulation. They're thinking, living, and breathing just like us -- completely indistinguishable.
Perhaps the fidelity and technology is even beyond our reasoning. Perhaps the future is able to bend physics and capture the past light cone. It may be able to perfectly simulate the past as it happened, down to every neurotransmitter fired by every brain at every second. Every event, every thought, every emotion. Perhaps it is pulling beings out of the past and placing them into its simulation with 100% fidelity such that you couldn't tell the two apart if you wanted.
What is it about understanding the universe that makes it such an axiomatic global objective? Sure for many of us myself included it's as all pervasive as the air we breathe... But sometimes I do wonder if it is actually all that correlated with my well-being.
Security is one area in which you can't really afford not to go down the tin foil hat rabbit hole. It's been like this for some time, where it's not really possible to know just how much capability is possessed by nation state actors, but with AI and other tools those capabilities will expand and become the baseline probably way sooner than we predict. No longer will experts be needed to do careful tracing to deanonymize, one of the true superpowers of AI will be its ability to extract the full power out of the big data we've been collecting. So the cost then of figuring something out that now might cost millions will soon cost a couple bucks.
It's relatively fast (probably could be faster than NVMe if optimized, i did not rtfm) and it is available. it's not the most horrible of ideas. I am fairly fairly certain lots of applications will load assets into vram and then evict them from system memory. Why not leverage this for general purpose use if it makes sense (after taking into account the security implications of course)?
This article started off really clear and straightforward, then it dove into stuff that I clearly wasn't going to be able to follow, and upon skipping it I arrived at the explanation which was was plainly obvious from common sense.
>such a number is often dutifully provided to such journalists, who in turn report it as some sort of quantitative demonstration of how remarkable the event was.
Apparently the conclusions are not common sense if you are a journalist.
Common sense can mislead, so it's instructive to make it rigorous to see whether it does indeed hold up. Not for everything or even most things, otherwise you'd be analysis paralysis sets in.
He also used common sense to determine he had no way of determining the probability of a rigged event. And therefore using Bayesian probability looked fancy but didn't help learn anything new. I remember reading first paragraph and thinking wow, bayesian has a way of helping determining the odds of that, but no.
Either he wanted to educate or is so involved with statistics that it became his default way of framing problems.
We "bought" a Samsung fridge last black friday. Something extraordinary happened. Their system failed to deliver us the fridge. We had to reschedule the delivery since we were staying at the parents' for Thanksgiving a few extra days. It just never got delivered. It seemed like it was XPO's screwup, but it was hilarious to me that they could not get their system working well enough to even get the fridge to show up at our house.
