It is a chat bot. It is a good compared to the chart bots we had in the past, but still a chat bot.
The reason it can be used for programming is because programming language is still a language.
They only seen to forget that programming languages were already invented to be a bridge between human and a machine language, but being able to do software engineering is much more than just knowing programming languages.
This makes me wonder, anyone knows how good are those tools at creating assembly code? I don’t program in assembly, but I know that the “language” is very simple, but you actually need to be constantly aware of the state of the system.
I’d suspect the low “density” of context makes it prone to hallucinations. You need to load in 3000 lines to express what Python does in 3, so there’s a lot of chances to guess the next token wtong.
I was gonna say that, probably the higher the abstraction level the best it is for LLMs to reason about the code, because once learned it’s less tokens.
Well, just keep pumping in the billions until the bubble bursts and we can look for the next fad, to do it all over again, right?
I have an idea guys what about like a big cloud we can put all our data in ?? Guys CLOUD. ITS SO GENIUS. CLOUD.
This ai shit is the exact same thing (also it isn’t ai. And I hate that we keep calling it that. )
It is a chat bot. It is a good compared to the chart bots we had in the past, but still a chat bot.
The reason it can be used for programming is because programming language is still a language.
They only seen to forget that programming languages were already invented to be a bridge between human and a machine language, but being able to do software engineering is much more than just knowing programming languages.
This makes me wonder, anyone knows how good are those tools at creating assembly code? I don’t program in assembly, but I know that the “language” is very simple, but you actually need to be constantly aware of the state of the system.
I’d suspect the low “density” of context makes it prone to hallucinations. You need to load in 3000 lines to express what Python does in 3, so there’s a lot of chances to guess the next token wtong.
I was gonna say that, probably the higher the abstraction level the best it is for LLMs to reason about the code, because once learned it’s less tokens.