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.
I'm currently working on a game despite not being very familiar with Unity. When I have some feature I need explained, or running into some bug in the game, I'd usually use Google and find some forum post that hopefully has a similar problem to mine and go from there. With GPT, I can just tell it the problem and get an answer, without scouring through multiple posts or having to constantly readjust my query. Yes, the information it produces might be incorrect, but I think the (time needed to verify the solution provided) is less than the (time needed to produce a search query that gets the articles you want * time needed to read each article and see if it helps me).
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.
The point of Minsky's action is to demonstrate to Sussman that Sussman's intent is essentially "if you can't see it, it's not there", but of course the room doesn't become empty when Minsky closes his eyes - the neural net won't lose preconceptions just because you randomly wired it, you just lose the ability to see and control what those preconceptions are.
Not sure if you're being purposefully ignorant or not so I'm not going to engage this discussion, but for anyone reading, this should be basic dietary knowledge
This is pseudoscience. As long as you consume a certain amount of calories and get your daily nutritions, you can eat whatever you want without getting obese. You can still become obese eating 3000 kcals of salad every day without exercising. Of course, healthy caloric intake will only ensure you don't become obese, you'll still be consuming way more fat/carbs than you should if you eat McDonalds, but it is certainly possible to create a "healthy" everyday-McDonalds diet (but you would be changing the meal to the point it won't be recognizable)
> This means valgrind cannot really detect memory issues as well since Odin has it’s own internal allocators. helgrind cannot work because Odin doesn’t use pthread primitives. ltrace cannot work because that just provides wrappers over every libc function, etc
Unfortunately, I've gone through too many bugs that had to be fixed through valgrind debugging that I'm unwilling to part with it
Good engineering. Midjourney likely has a lot going on under the hood before your prompt actually gets to Stable Diffusion. As an example you can check out this research paper [0] which seeks to add prompt chaining to GPT-3 so you can "correct" it's outputs before it reaches back to the user. There's also no rule that states you can only make one call to SD, MJ likely bounces around a picture through a pipeline they've tuned to ensure your generated image looks more reasonable.
I think that's amazing on its own. Rather than having to do a leetcode hard on the fly, you can just ask for the solution. You'll still need to know the problem space in order to properly optimize it, but it can save a lot of time.
The 'eternal struggle' is such an interesting concept and I've thought about it a lot. It really does seem like, while true happiness may not solely come from overcoming challenges, if those challenges aren't present you definitely won't be happy. I think this aligns better than the top post's idea of "smart people see the awful things that can't be changed", it's moreso that smart people aren't finding satisfying challenges in the first place. I remember when I went wild downloading ROMs for games when I found out that was thing; once I ended up with all the games I wanted to play, I lost most of my interest to play any of them.
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.
One thing that immediately stood out to me is the mention of Developer Tools. Most laypersons don't even know it exists. I'm wondering if it's possible for Google to make the presentation of things like meta tags and descriptions more user-friendly? Like, a small banner or icon when your mouse is at the top of a page or even an icon in the address bar, when you click it, it shows you things like the meta and description
> Same thing with my TV and Router, both of which required an app to just setup
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
Solved in 1:39, very fun game and great implementation! I'm not much a fan of pipes games but have played similar concepts such as Infinite Energy on mobile. This is a good job for such a quickly developed project
>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.
> But I imagine Rails is being increasingly dismissed by newbie developers as being obsolete and not-cool. Mature companies may realize it's in their best interest to communicate that their boring-tech works just fine and that they have no plan on changing to cool-tech
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.
Felt the opposite, he really exuded that cold-and-carefree-but-wise archetype I'd expect from a mid-2000s cocky hedge fund manager who got themselves into that position in the first place.