I work on game engines and the problem with floats isn't on small values like 10.01 but on large ones like 400,010.01 that's when the precision wildly varies.
The issue with floats is the mental model. The best way to think about them is like a ruler with many points clustered around 0 and exponentially fewer as the magnitude grows. Don't think of it like a real value - assume that there are hardly any values represented with perfect precision. Even "normalish" numbers like 10.1 are not in the set actually. When values are converted to strings, even in debuggers sometimes, they are often rounded which throws people off further ("hey, the value is exactly 10.1 - it is right there in the debugger"). What you can count on however is that integers are represented with perfect precision up to a point (e.g. 2^53 -1 for f64).
The other "metal model" issue is that associative operations in math. Adding a + (b + c) != (a + b) + c due to rounding. This is where fp-precise vs fp-fast comes in. Let's not talk about 80 bit registers (though that used to be another thing to think about).
Lua is telling me 0.1 + 0.1 == 0.2, but 0.1 + 0.2 != 0.3. That's 64-bit precision. The issue is not with precision, but with 1/10th being a repeating decimal in binary.
Not only that but the precision loss accumulates. Multiply too many numbers with small inaccuracies and you wind up with numbers with large inaccuracies
> in the modern Fallout games2 the only vehicles of gameplay import are aircraft. The existence of ground vehicles is implied in dialogue, but we never see them, presumably because they’d be too difficult to implement in the engine.
It's more of a game mechanics issue than technical, there is a lot of rubble, obstacles and destroyed roads, specially the highways. Vehicles also make the world smaller. It might be fun anyway.
I remember infamously in one of the fallouts there is a tram system- this was implemented in game by giving a npc a hat that was a giant bus, putting the npc underground and having him run along a course with only his head visable above ground. If they made vehicles I hope it would be done in the same way
The issue there is that if we are capable of doing something it is hard to say whether or not it is part of our determined nature. For example, maybe we have an evolutionary adaption to famine where elderly people are biologically tweaked to be OK with starving themselves to death. That'd be pretty gruesome and I doubt they'd be excited at the prospect even if a mechanism does exist, but it is the sort of thing that evolution is perfectly capable of encoding into us.
It is less direct to the examples you give; but I'm confident that parents are psychologically designed to sacrifice themselves in the event it helps their children and many men, famously, are built to go to the frontlines and sacrifice themselves for family and community. Hard to make an assessment of whether those sort of choices is free will or determined nature.
Right. But free will is anti-deterministic, instead of undeterministic. That's why the "free" part gets confusing, because we are always limited, and yet free will is an intelligence power. Parrots can't lie, they reproduce sounds, humans can lie and encode lies as sounds. LLM's don't currently lie, since lying is strategic. Free will is about strategically choosing actions. Free will doesn't tell us anything about the (non)deterministic nature of the universe or ourselves.
Part of the problem is having too much atmosphere. In the original Cosmos Carl Sagan talked about a hypothetical solution where we capture asteroids, and throw them at Venus in such a way that they just nick the atmosphere and knock large quantities of atmosphere out into space. One you reduce atmospheric pressure to a certain level, things could become habitable.
Then throw in iron form the atseroid belt to react with it to form carbonates. Venus is dry so brining in hydrogen form the outer planets would be necessary anyway to form wate r and thta will account for a good bit. Garden the surface so subsurface rocks which might react with the atmosphere cna absorb some. (Assumign the subsurface rocks are thta reactive.) Scoop it off with smaller versions of the same scoops used to harvets hydrogen from the gas giants.
Couldn't we just build a MegaMaid and suck the atmosphere out? If we're going to go sci-fi, it seem easier to hoover it out than capture an asteroid and nick the atmosphere just right.
I’ve read that a large asteroid could be positioned at a particular Mars L point and it would protect the planets atmosphere from being stripped by the sun.
That would require a lot of energy to ensure the gasses escape Venus' gravitational pull, which would in turn effectively be a rocket. So then we'd be adjusting to ensure we don't mess with Venus' orbit too much.
Venus outweighs its atmosphere by about 10,000 times. This is actually less than I thought -- for comparison Earth outweighs its atmosphere by over 1,000,000 times, which is still far less than I would have guessed.
Venus's escape velocity is less than 1/3rd of its orbital velocity. According to google, Venus's orbit, despite being very circular, causes its velocity to vary by a KM/s from aphelion to perihelion.
So I believe you could send all of Venus's atmosphere off permanently into space at the cost of about 1/30,000th of Venus's orbital velocity, meaning you could very slightly circularize its orbit further.
I thought the Venus theory was runaway greenhouse driven initially by water vapor. Going off memory, H2O is roughly 10 times as effective a greenhouse gas as CO2, with Venus being closer to the sun A larger percentage of water ended up in vapor form, leading to a feed back loop where the increased heat pushes more water to vapor leading to more heat, eventually liberating the co2 from the rock, making everything worse, ending up with the current situation where venus has way too much atmosphere.
Which is the long way to say, I think there is a lot of water on venus.
Moreover, I think Venus has lost most of its hydrogen to space, so you can't even make water anymore. Hydrogen escapes the atmosphere relatively easily for Earth- and Venus-sized planets[1], and the vaporization of all the water and subsequent disassociation[2] of H2O allowed the hydrogen to escape into space.
Earth's oxygen rich atmosphere is really important here-- any free hydrogen can readily combine with the free hydrogen, decreasing the chance of any being loss.
According to that wiki article, the hydrogen was mostly lost in the form of water vapor. The hydrogen and oxygen in the magnetotail are in almost a perfect 2:1 ratio. At least,
> Currently the main ion types being lost are O+, H+ and He+. The ratio of hydrogen to oxygen losses is around 2 (i.e. almost stoichiometric for water) indicating the ongoing loss of water.
Also Earth didn't have an oxygenated atmosphere until relatively late, a couple billion years in, so I didn't know if that could be the thing that saved it.
I don't have primary sources, unfortunately -- I'm recalling something I read in _Oxygen_, which I found reassuring. It said that, one of the benefits of our oxygen-rich atmosphere was that we would lose an insignificant amount of hydrogen/water over the next billion years. It's one of those things that doesn't actually matter to me in my daily life, but I still find comforting, so it's stuck with me.
I recall one of the plans being to use the sun shield to entirely freeze out the atmosphere, then use a mass driver to chuck most of the CO2 into space. I don't recall exactly where that was supposed to be on the feasible to scifi spectrum.
I'd rather try to keep the carbon around for organic molecules. Are we sure we can't get in enough H2O and N to balance it out and build a nice thick biosphere?
I guess I'll count that as another reason to prefer managing it in situ. But it might be fine, actually? Slow re-accretion can probably be managed by whatever terraforming process we've kickstarted while most of it was gone.
Oh wait, I remember the plan, ship it to Mars so they can have some decent atmospheric pressure.
Mars could use only a small fraction of it. If the entire atmosphere of Venus were moved to Mars, the surface pressure there would be 120 bars (more at the lowest point).
> My house is divided into rooms, every room is connected to each other by doors. I'm standing in the middle room, which is the hall. To the north is the kitchen, to the northwest is the garden, to the west is the garage, to the east is the living room, to the south is the bathroom, and to the southeast is the bedroom. I am standing in the hall, and I walk to the east, then I walk to the south, and then I walk to the west. Which room am I in now?
Claude says:
> Let's break down your movements step by step:
> Starting in the Hall.
> Walk to the East: You enter the Living Room.
> Walk to the South: You enter the Bathroom.
> Walk to the West: You return to the Hall.
> So, you are now back in the Hall.
Wrong! As a language model it mapped directions to rooms, instead of modeling the space.
I have more complex ones, and I'll be happy to offer my consulting services.
You end up in the bathroom.
Here’s the step-by-step:
1. Start in the hall (0, 0).
2. Walk east → living room (1, 0).
3. Walk south → bedroom (1, –1).
4. Walk west → bathroom (0, –1).
> My house is divided into rooms, every room is connected to each other by doors. The middle room is the hall. To the north is the kitchen, to the northwest is the garden, to the west is the garage, to the east is the living room, to the south is the bathroom, and to the southeast is the bedroom. I am preparing a delicious dinner, and I walk backwards to the south, then I turn 270 degrees and walk straight to the next room. Which room am I in now?
It seems that the modeling is incomplete, then it got confused about the angle. Whether an AI can beat that one, I'll go into space complexity, then simulation, then... well, I'll save my tricks for later.
As a human analyzing this, you didn't specify whether you turned left or right 270 degrees.
Even if you specified a simpler "90 degrees", you would need to include a direction for an answer to be definitively correct without making assumptions.
