Print

Please login or register.
1 Hour 1 Day 1 Week 1 Month Forever
Login with username, password and session length

[Neonivek]

It just shows how dependant we are on updates, really.  This is what happens after a week without them.  It's kinda sad.

I always picture Toady getting sicker when that sort of stuff happens. Like some sort of sympathetic link has been formed.

[Lord Shonus]

Anyhow as for animals, several things could be done... though I am not sure how helpful they could This isn't even including creatures such as Tunuki, Faeries, or even Djinn that don't even have consolidated mythos and have been both extremely malicious and malevolent (Which can be handled either by making them two different creatures or by giving the creatures the capacity to be either).

Did you mean malicious and benevolent?

[tfaal]

Though to admit the one thing I personally think has more problems, and will aggrivate me more, is the "Fantasy Ark". Too many monsters have motives, powers, weaknesses, and ethics that the game simply doesn't handle (and likely never will) and thus in order to fit them all in they will have to be butchered and cookie cut into the game. This isn't even including creatures such as Tunuki, Faeries, or even Djinn that don't even have consolidated mythos and have been both extremely malicious and malevolent (Which can be handled either by making them two different creatures or by giving the creatures the capacity to be either). I really would rather have them done somewhat right then done.
-That and people will probably try to put in things like Cthuhu, Dungeons and Dragons monsters, and stuff.

Not sure I see any problems here. Having good/evil versions of one creature could be handled rather elegantly with castes, Tanuki and fairies would be quite similar to gremlins (intelligent, mischievous, uncivilized critters) and could be done up in much the same way, and Djinn could be done rather well with megabeasts. Also, Forgotten Beasts/Evil Titans pretty much mean that Cthulhu is in vanilla DF next version.

[Toastergargletop]

contibuting

sorry, i was just trying to tip it over the 666.  no particular reason, but goddamn it i want the new release :/

[smjjames]

Hmm, just a random thought out of the blue:

Will there be or will it be possible to have titans/forgotten ones (or old ones, elder gods, however you want to call them) which are completely non-organic in nature? Could range from a golem-like thing to something resembling a mecha or a construct like the bronze colossus.

Given the new material stuff (round shelled blob of goo anybody?), I'm sure its possible, but have you seen titans that would resemble something that is an artificial construct in your journeys through the legends of the worlds you made?

[Footkerchief]

Will there be or will it be possible to have titans/forgotten ones (or old ones, elder gods, however you want to call them) which are completely non-organic in nature? Could range from a golem-like thing to something resembling a mecha or a construct like the bronze colossus.

Yes, that's all possible.  For most purposes the game doesn't care whether a creature's materials are "organic" or not.

[smjjames]

I know the game doesn't make any distinction between organic and nonorganic, hell, you can even have sand or magma for blood in the next version. I was just saying non-organic as a concept, as in metal, glass, or even rock*, to make it clear what I was talking about.

A cyborg (half organic and half something else that is not neccesarily machine) titan/forgotten one would be cool as well though.

Edit: What can I say, I like science fiction and technological stuff.

*Some rock types can be organic in origin, coal deposits for example, but thats besides my point.

[Footkerchief]

I know the game doesn't make any distinction between organic and nonorganic, hell, you can even have sand for blood in the next version. I was just saying non-organic as a concept, as in metal, glass, or even rock, to make it clear what I was talking about.

Yes, I know what you meant, and that's what I was answering when I said

For most purposes the game doesn't care whether a creature's materials are "organic" or not.

There is, for example, no material tag that directly tells the game that a material is stone or metal, although the ITEMS_METAL tag tells the game "this material can be used to make items that can be made out of metal."  Likewise, materials you'd consider organic just have circumspect tags like IMPLIES_ANIMAL_KILL and STRUCTURAL_PLANT_MAT.  They're all just materials.  From the game's perspective, making a creature out of "organic" muscle tissue isn't any more or less strange than making it out of "inorganic" iron.

Also, Toady specifically mentioned forgotten beasts made of glass in DF Talk 3.

[G-Flex]

Hrm. Does the game handle brittleness at all? After all, a glass creature might be hard, but it also might be kind of brittle, depending on thickness.

[Neruz]

Brittleness is sort of implimented with elastiscity and shear force.

[Footkerchief]

Hrm. Does the game handle brittleness at all? After all, a glass creature might be hard, but it also might be kind of brittle, depending on thickness.

Yes, it does.  Basically, the closer the tensile/torsion/compressive/shear yield point is to the fracture point, the less a material will deform before breaking:

In game terms, the yield=fracture means that if you manage to hit the adamantine hard enough, it won't dent but will fracture immediately.

I imagine that glass also has yield=fracture, but with much lower numbers.  The glass materials aren't in the raws, though, so it's hard to verify that.

[CobaltKobold]

Tarn did say that fracture propagation was NOT properly done, that striking the marble golem in the shoulder with a chisel won't cause a crack to run down the torso.

edit: sourcing

There are a couple of notions at work here, and we've got one and not the other.  The stone would be damaged, and break in that sense, but there's no notion of overall cleavage/fracture/whatever type characteristics.  Some things should shatter into little pieces, or break off in sheets, or whatever else.  So right now, you'd plant your pick into the stone colossus, but it wouldn't get appropriate larger fractures spreading over itself.  Modeling that sort of thing isn't out of reach, at least in a rough yet effective way, but it's not going in this time around.

[G-Flex]

I believe that there he's talking about different types of fracture, though, and not the overall notion of things being more difficult to fracture than other things.

[Shoku]

There's a reason in the real world why cheetahs and kangaroos (for instance) don't live together.

Different organisms exist in different ecological niches. You can't just mix and match types that can theoretically live in the same areas and expect everything to be okay. That's why invasive species are bad.

Yes but how the hell is the game going to recognize this with only general info like roaming and carnivore?

Ecology is a pain in the butt and no automatic worldgen system is going to take enough things into account to make people happy. You could do a passable job of it by defining a diet type and how much food something needs available but it might turn into a nightmare for making lots of species like in the ark project. In real life throwing more food into a location tends to allow fewer species because of the complex tradeoffs survival demands and the ways different species limit each other. On Earth we've really only got grass because of all the grazing animals that suck up more bushes and trees when they're small and there are horrendously complex relations between the animals themselves.

It's hard enough to just deal with vitamin intake for dwarves much less doing all of that for every species as well as modeling if they can find shelter and mates and so on.

So what I'm really getting at is that you're asking for magic solutions. "Let's make it incredibly complex but also not processor intensive."

On the subject of material properties, hasn't anyone asked a chemist (geologist, metallurgist) about some complete list? I thought these kinds of things had been tested and recorded before...Just in case, I'll ask my teacher/professor next time I get a chance (AP classes FTW...yet there are only 37 people out of ~320 in chemistry).

 DF is mainly theoretical; insanely accurate theory. I think the niche system could work, but only if it somehow accounted for the minor differences between animals. As the world is generating, numerous species would be wiped out from the imbalance, and others would be successful. I think if we brought the initial diversity high enough, this would just lead to a different semi-balanced world each time (I just visualized arctic marsupials for some reason, but that would require an adaptation system). It's kinda like how sometimes elves, goblins, humans, or dwarves have been wiped out by game start. Sometimes all of them if orcs are involved.

 I was "ninja'd" by Footkerchief; this is why I must conquer my attention span.

Well for a basic system with moderate complexity and realism you could start off by deciding how rich the soil was. Really poor and you get a few species of plants that do well in crap conditions, really rich and you get a few species of plants that can grow faster than others, and somewhere in between you get the most variety.

Then depending on the variety of plants you choose a range of herbivores for the area. There can be some similar scarcity vs abundance stuff going on for them. Having them eat certain plants to extinction is probably too complex for this so none of that.

Then you could technically do primary, secondary, and tertiary predators but I'd say just have a single range for them, maybe weighting species by size so that having some big predators around sucks up the food maybe three small predators would eat.

This borders really close to the idiot grade system from Spore but it would be easy enough to follow. Sticking to slightly higher standards though this would be a good enough way for initially dealing out the cards and then we could have some parameter in the raws for effectively how far they could travel in other biomes (maybe with some weighting so that deserts were like a brick wall for things from tropical areas and mountains were pretty rough for most things unless they fly.)

At this point with some species having spread out from their starting points into potentially several biomes we could do the localized sub-species sort of thing I talked about earlier with shifted characteristic probabilities but maybe we don't care about that.

If dynamic biome borders ever become a possibility this could also result in previously connected populations being split but this is really hitting the border of practical plans so there's not much value in trying to discuss it.

It would probably be more functional to be able to list 'companion' creatures in the creature data. When a creature is seeded into a biome, it's more likely to place it's 'companion' creatures in the biome and less likely to place non companion creatures into the biome.

Defining graph relationships in the creature raws would be very messy and difficult to maintain.  I'd move toward a hierarchical system at least, i.e. grouping creatures in some fashion.

How about describing food characteristics for each creature, then matching predators up with prey? Perhaps some info about hunting characteristics would help there too, such as wolves hunting in packs, or giraffes having long necks.

For example, a tiger might be able to kill anything up to the size of a horse if it doesn't have good offensive weapons. Or a snake might be able to eat anything that it could swallow that doesn't have spines.

For niche-type distinctions you could probably just give it a value with the meaning of specialized diet vs generalized diet. You can cram more specialists into an area before they conflict with each other while generalists do well when there's not enough of any one food source in an area.

You might end up with giraffes unrealistically competing with humming birds but with a good assortment we can just assume that after so many herbivores they've figured out every way to eat the available plants or act like it's changed into a matter of having available space to pick a home. Carnivores obviously get a separate bracket but the same general system could work.

I think a simple, if hackish, temporary solution is to only allow a certain number of each "category" of animal in each region. For example, a region might support ten or eleven kinds of small herbivores (rabbits, squirrels, etc.) four or five kinds of medium herbivores (Horses, zebra, etc.),  and two or three kinds of large ones (moose, elk, elephant, etc.), and one extra-large species (Triceratops, Brachiosaurus, etc.) Use a similar pattern for predators, with smaller populations. Not extremely realistic, but it would make each region distinct.

Th ebiggest issue with invasive species is not that they are better adapted for the environment, but that the ecosystem is badly adapted to them. Had the bunny evolved in australia, it would not have been so destructive.

More like it would have squeezed out competition on a longer time scale and we'd have never seen the species that went extinct. There is some degree of "early competition would have spawned an arms race instead of overnight domination" at play in that sort of thing but the actual survival style of species is typically very rock-paper-scissors and one species is bound to lose to another with it's only hope being to move to a different niche.

It's like a few weeks worth of lectures to explain the actual population dynamics and how to tell if two competing species can coexist so just take my word about it not being worth sticking in the game :b

what about having generic template creatures and have them "adapt" in a generic simplified way? we could end up with large wolves hunting mountain elephants, and being named after the region they exist on, we'd be starting with real world animals, but fantasyfying them on the run

ofcourse this would have to be done with a bit more sesearch, so we could get a significant variety in characteristics, instead of just having biger or smaller, brands of the same animal

Well if you've kept up with how entities work now you've got values for things like how far apart the eyes are and how big ears are for dwarves all with probability ranges so you should be able to tweak a whole lot of things for subspecies.

As for colors mammals primarily have a yellow pigment for hair that ends up brown at high concentrations and black at higher concentrations. There's a little voice in the back of my head telling me I've made a blunder in that description but I can't quite pick out how the system works for real but we could basically define colors as being related to each other in this way and have the transitions between them be available while fancy colors could show up rarely in the subspecies.

Depending on how diet is defined you could have the subspecies changing that as well.

2) Animal grouping: If we have 10 different wolves and 100 other canine creatures. Having 5 exist in one biome may be excessive.

How's the game supposed to recognize that a dingo and a wolf have any relation? We gonna have to juggle templates for artificial connections?

[G-Flex]

There's a reason in the real world why cheetahs and kangaroos (for instance) don't live together.

Different organisms exist in different ecological niches. You can't just mix and match types that can theoretically live in the same areas and expect everything to be okay. That's why invasive species are bad.

Yes but how the hell is the game going to recognize this with only general info like roaming and carnivore?

I never said it should. Obviously the game would need to keep track of more complex behavior and predator/prey interactions.

Ecology is a pain in the butt and no automatic worldgen system is going to take enough things into account to make people happy.

Yes, it's difficult, and it can't be perfect. That doesn't mean that isn't at all possible. You could make the same argument about a lot of things DF already has or will have in the next version. If the game can use different values concerning the elasticity of a material and reasonably apply them to things like combat, then there's a good case for complex behavioral and physical traits to be represented in ecology.

It's not as if things as difficult as this aren't routinely mentioned by Toady as part of the development plan.

So what I'm really getting at is that you're asking for magic solutions. "Let's make it incredibly complex but also not processor intensive."

I don't believe I ever said anything of the sort. Also, worldgen is a point where you can deal with things being a bit more computationally expensive, because it's a fixed-cost thing; the world taking longer to generate doesn't affect gameplay.

And again, I don't think I or anyone else is claiming that an ecological simulation can be perfect or take everything into account. But it can still exist to some passable degree or another.