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.
I assumed I knew what `and get charged extra if they want them to act a certain way or do certain things` meant, but maybe not. I thought it was along the lines of acting romantic/sexual/etc. Maybe I'm way off but I'd think otherwise it would just be an AI friend.
I didn't know AI girlfriends were a thing until I clicked on this post today.
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.
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)
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
That "calorie is a calorie", or "every calorie counts", is not a basic dietary knowledge, it's a myth/lie promoted by a food industry.
You can keep believing the ads, or just search the term in google/duckduckgo and spend 5
minutes reading different sources.
Just a few examples (first link from a search engine):
"Fiber. You eat 160 calories in almonds, but you absorb only 130. The fiber in the almonds delays absorption of calories into the bloodstream, delivering those calories to the bacteria in your intestine, which chew them up. Because a calorie is not a calorie.
Protein. When it comes to food, you have to put energy in to get energy out. You have to put twice as much energy in to metabolize protein as you do carbohydrate; this is called the thermic effect of food. So protein wastes more energy in its processing. Plus protein reduces hunger better than carbohydrate. Because a calorie is not a calorie.
Fat. All fats release nine calories per gram when burned. But omega-3 fats are heart-healthy and will save your life, while trans fats clog your arteries, leading to a heart attack. Because a calorie is not a calorie.
Sugar. This is the "big kahuna" of the "big lie." Sugar is not one chemical. It's two. Glucose is the energy of life. Every cell in every organism on the planet can burn glucose for energy. Glucose is mildly sweet, but not very interesting (think molasses). Fructose is an entirely different animal. Fructose is very sweet, the molecule we seek. Both burn at four calories per gram. If fructose were just like glucose, then sugar or high-fructose corn syrup (HFCS) would be just like starch. But fructose is not glucose. Because a calorie is not a calorie."
I'm very fascinated by the idea that part of the issue with ultra-processed foods is that the calories are more bioavailable due to the lack of fiber and protein.
3000 kcals of salad is huge in terms of volume, so getting obese is practically impossible on such a diet unless it was drowned in dressing. Bodybuilders that are on a cutting phase actually consume higher volume / lower calories foods to still feel satiated.
Kale is one of the most calorie dense leafy greens and it tops out at 80 kcal per 100 grams, meaning you'd need to eat about 3.7 kilograms of kale to get 3000 kcal.
> 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
The Odin team are working to put valgrind, helgrind, callgrind, memcheck, etc in to the Odin core library to provide better debugging tools! Along with many other debugging tools.
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.
