I'm an AI nerd and yes, nowhere close. AI can write code snippets pretty well, and that'll get better with time, but a huge part of software development is translating client demands into something sane and actionable. If a CEO of a 1-man billion dollar company asks his super-AI to "build the next Twitter", that leaves so many questions on the table that the result will be completely unpredictable. Humans have preferences and experiences which can inform and fill in those implicit questions. They're generally much better suited as tools and copilots than autonomous entities.
Now, there was a paper that instantiated a couple dozen LLMs and had them run a virtual software dev company together which got pretty good results, but I wouldn't trust that without a lot more research. I've found individual LLMs with a given task tend to get tunnel vision, so they could easily get stuck in a loop trying the same wrong code or design repeatedly.
Now, there was a paper that instantiated a couple dozen LLMs and had them run a virtual software dev company together which got pretty good results
Dude, you need to take a closer look at that paper you linked, if you consider that "pretty good results". They have a github repo with screenshots of some of the "products", which should give you some idea https://github.com/OpenBMB/ChatDev/tree/main/misc .
Not to mention the terrible decision making of the fake company (desktop app you have to download? no web/mobile version? for a virtual board game?)
(Also the paper never even tried to prove its main hypothesis, that all this multi agent song and dance would somehow reduce hallucinations and improve performance. There is a lot of good AI stuff coming out daily, but that particular paper - and the articles reporting on it - was pure garbage.)
I'm an AI nerd and yes, nowhere close. AI can write code snippets pretty well, and that'll get better with time, but a huge part of software development is translating client demands into something sane and actionable. If a CEO of a 1-man billion dollar company asks his super-AI to "build the next Twitter", that leaves so many questions on the table that the result will be completely unpredictable. Humans have preferences and experiences which can inform and fill in those implicit questions. They're generally much better suited as tools and copilots than autonomous entities.
Now, there was a paper that instantiated a couple dozen LLMs and had them run a virtual software dev company together which got pretty good results, but I wouldn't trust that without a lot more research. I've found individual LLMs with a given task tend to get tunnel vision, so they could easily get stuck in a loop trying the same wrong code or design repeatedly.
(I think this was the paper, reminiscent of the generative agent simulacra paper, but I also found this)
Dude, you need to take a closer look at that paper you linked, if you consider that "pretty good results". They have a github repo with screenshots of some of the "products", which should give you some idea https://github.com/OpenBMB/ChatDev/tree/main/misc .
Not to mention the terrible decision making of the fake company (desktop app you have to download? no web/mobile version? for a virtual board game?)
(Also the paper never even tried to prove its main hypothesis, that all this multi agent song and dance would somehow reduce hallucinations and improve performance. There is a lot of good AI stuff coming out daily, but that particular paper - and the articles reporting on it - was pure garbage.)