802 karma · joined April 30, 2019
Llama 30B 4-bit has amazing performance, comparable to GPT-3 quality for my search and novel generating use-cases, and fits on a single 3090. In tandem with 3rd party applications such as Llama Index and the Alpaca LoRa, GPT-3 (and potentially GPT-4) has already been democratized in my eyes.
Here's an example regarding grounded characters sticking to walls:
prompt: Thanks! I added walls and ground to my game, as well as detection so that if the player touches the ground, they will be in a grounded state. However, when the touch the vertical face of the ground/wall, they stick to it. Can you tell me what I'm doing wrong?
response: It seems like the issue you're encountering is related to the physics and collision detection in your game. The player is likely detecting the wall as the ground, and it's causing the grounded state to be triggered when it shouldn't be. To fix this, you can modify your ground detection code to take the angle of the surface into account.
Here's a solution using the Physics.Raycast method:
Assuming you have a LayerMask called groundLayer for ground detection, make sure the ground and walls are assigned to the appropriate layers in the Unity Editor
[...further details on using angle detection on collision, as well as accurate sample code]
I can even ask it to give me the reference for the _Physics.Raycast_ method:
response: Certainly! Here's the official Unity documentation for Physics.Raycast:
[URL to official docs filtered out by HN]
Physics.Raycast - Unity Manual The Physics.Raycast method allows you to perform raycasts in your scene to detect collisions with 3D objects.
[...further information on how to use it, including an accurate code example pulled from the docs]
This just drastically reduces time-to-solution, especially when you consider you can lazily leave out information and still get a good response.
In short, I treat it as though each session is a fine-tuned search engine and get a lot of value from it, but it doesn't completely replace forums or Youtube videos, for one it can't argue with itself to provide conflicting but valid alternate solutions - I'd have to argue with it/ask it to produce those.
Unfortunately, I've gone through too many bugs that had to be fixed through valgrind debugging that I'm unwilling to part with it
Truth
My headcanon is that it's tied to the fact that our life spans are limited and we've evolved to derive the most satisfaction when we're working on a task that is difficult for us individually or has vague success criteria, which seems to match up in part with the article's takeaway. It's also how I reason that not only fucking things up, but also complaining about it and trying to fix it are all required for people to feel happy. I see this ethos in a lot of old religions as well - humans striving towards the same qualities as a godhead but never quite getting there no matter how awesome their abilities become, or how our 'perfect' state was when we were ignorant of the consequences of our actions.
Off the top of my head, both Xfinity and Google Home have this problem and it aggravates me to no end. I can reset my gateway from my PC but for some reason, *need* to use my phone to manage Xfinity or any of my Nest routers
>I'm not sure what you mean by "load image in black and white ttf c++", but I can give you an example of how to do it. First, you'll need to convert the image to grayscale. You can do this by using the cvtColor function. Then, you can apply a binary threshold to the grayscale image. For example, if you have a color image with a value of 255 and a black value of 0, then you can do something like this: __
First impressions - really impressive! I did have to add "c++" to get any meaningful results though.
I dont think that's the case. I think Ruby is dismissed because it's not a boring language, but has none of the safety of the other "shinier" languages.
It was not invented, that was the first time the euphemism was correlated. Having knowledge of the history of "to be disappeared" and having knowledge of what "being disappeared" brings to mind, are two very different things.
The only way you could justify a statement like this is by ignoring at least two events that both hit closer to home to Americans - the kidnappings done by the Gestapo in the 30s and the Mafia in the 20s. I stand by my statement that the Dirty War in Argentina is not something that comes to mind for most Westerners when someone uses the phrasing of being "disappeared"
Now, you add in things like torture and detainment. I mean, whatever. Feel free to die on this hill. My post's point is that the vast majority of society does not think of the Dirty War, or any sort of violence, when they hear the phrase "I was disappeared".
I'm not sure what I'm supposed to take away from this: I did explain further the context of obsessive generalization, but I'm not sure how, given you yourself say you're well read on leftist literature, you can't correlate how extreme egalitarianism requires doing away with individual characterization.
>The leftist ideal is actually that all people are free to pursue their passions and creativity
Wouldn't that imply that leftism cannot exist without allowing fascism to also exist? I don't see how you can juggle this with the view that leftism's goal is to reduce oppression, given that the definition you've provided here necessitates that opression must be possible for leftism to achieve its goals. In my mind, assuming I'm reading into this correctly, is that you've created your own "chicken vs the egg" paradox
On obsessive generalization: You are approaching it from a purely economic perspective. I think it's disingenous to ignore the social goals of leftist theory, which are firmly rooted in removing the class concept entirely - obsessive generalization.