151–160 of 303 posts
Is there a post somewhere where I can get all the jargon for this AI/ML stuff? I have a vague understanding but I’m really sure what “weights”, “LoRA”, “LLM”, etc. are to really understand where each tool and concept fit in.
Is there a post somewhere where I can get all the jargon for this AI/ML stuff? I have a vague understanding but I’m really sure what “weights”, “LoRA”, “LLM”, etc. are to really understand where each tool and concept fit in.
I was like this a week ago. Basically, weights are numbers you feed to each neuron in the model, LoRA is a technique to adjust only some of the weights so you can fine-tune the model fast and on cheaper hardware, llm is a "large language model". I've been asking chatgpt4 these things and learning at my own pace and context: https://rentry.co/vafkn
It's frankly amazing how much information is summarized into those weights. You do need to take whatever it says with a very healthy pinch of salt. It doesn't know everything and it gives incorrect answers with an air of confidence. Here's an example: > who preceded emperor Commodus? The first emperor of Rome was Nerva (98-100 AD). He succeeded Domitian and came to power after a brief civil war in 69AD, which saw the…
now it just needs to be instructed to tell the truth , the whole truth and nothing but the truth
Genuinely curious since I don't want to brick my mac :) - It seems that there are more than a handful of segmentation faults happening for various users running this program on their Mac's. Is there a possibility that this may cause system wide stability issues? Wondering if the MacOS user program space is well isolated that these problems are a thing of the past and/or other environments? Also, ChatGPT seems ambival…
If by "past" you mean "1980s" and "other environments" you mean DOS, yes. I suppose it's still a problem for FreeDOS, but I recommend against trying to run ML models in it.
General Relativity is the theory that explains how gravity works. It says that space and time are connected, so if you go faster than light speed in one direction then when you come back around it will be slower because of all those extra miles traveled! This means there's no way to travel through a black hole or wormhole without getting sucked into them. General Relativity also says that gravity is actually the same thing as acceleration, so if something has mass then you can think about it like an object on Earth with weight pushing down from above and pulling upwards!
Genuinely curious since I don't want to brick my mac :) - It seems that there are more than a handful of segmentation faults happening for various users running this program on their Mac's. Is there a possibility that this may cause system wide stability issues? Wondering if the MacOS user program space is well isolated that these problems are a thing of the past and/or other environments? Also, ChatGPT seems ambival…
=> write a haiku about leaves Autumn's golden hues - Leaves of red, yellow and blue! \ #haikupoetry #leavesshort[1] > segmentation fault ./chat Interesting.
> write a typescript program that read a text file and print to the screen
const inputFile = './input.txt'; // path to your txtfile let outputString; // string variable for printing out contents of .txt files // open up our file, if it exists try { fsReadStream(inputFile); } catch (e) {} if (!!errno) throw errnoError(); /* Throw an error on ENOENT */ // if the inputfile does not exist // read in contents of file and print out to screen [1] 51232 segmentation fault ./chat
It's frankly amazing how much information is summarized into those weights. You do need to take whatever it says with a very healthy pinch of salt. It doesn't know everything and it gives incorrect answers with an air of confidence. Here's an example: > who preceded emperor Commodus? The first emperor of Rome was Nerva (98-100 AD). He succeeded Domitian and came to power after a brief civil war in 69AD, which saw the…
My current test is to ask them to write a three paragraph introduction to me for a departmental seminar (the kind of thing I hate doing). Thus far, none of them have managed to do it without introducing factual errors - wrong degrees (or institutions), wrong research focuses, etc. But they're all credible sounding in their wrongness.