After seeing this graph about the fall of StackOverflow, it’s clear to me that I’m not the only one who has stopped using it in favor of LLMS (large language model) alternatives. With the rise of generative AI-powered initiatives like OverflowAI by Stack Overflow, and the potential of ChatGPT by OpenAI, the landscape of programming knowledge sharing is evolving. These AI models have the ability to generate human-like text and provide answers to programming questions. It’s fascinating to witness the potential of AI as a game-changing tool in programming problem solving. So, I’m curious, which AI have you replaced StackOverflow with? Share your favorite LLMS or generative AI platform for programming in the comments below!
I do not use AI to solve programming problems.
First, LLMs like ChatGPT often produce incorrect answers to particularly difficult questions, but still seem completely confident in their answer. I don’t trust software that would rather make something up than admit that it doesn’t know the answer. People can make mistakes, too, but StackOverflow usually pushes the correct answer to the top through community upvotes.
Second, I rarely ask questions on StackOverflow. Most of the time, if I search for a few related keywords, Google will find an SO thread with the answer. This is much faster than writing a SO question and waiting for people to answer it; and it is also faster than explaining the question to ChatGPT.
Third, I’m familiar enough with the languages I use that I don’t need help with simple questions anymore, like “how to iterate over a hashmap” or “how to randomly shuffle an array”. The situations where I could use help are often so complicated that an LLM would probably be useless. Especially for large code bases, where the relevant code is spread across many files or even multiple repositories (e.g. a backend and a frontend), debugging the problem myself is more efficient than asking for help, be it an online community or a language model.
I might be taking over at a job for a friend who’s leaving the country. Not programming, but IT and Sec.
I was concerned about my lack of exp.
They told me just to use ChatGPT 'cause that’s what they do.
They don’t even have .exe files blocked for users.
I’m now far more concerned about the state of the networks I’ll be taking over. Going to be doing a full security audit as soon as I’m up to speed.
TT_TT
I was starting to think I was using LLMS wrong but you perfectly summarized my situation.
This is definitely my issue. I’ve experimented with LLMs for code generation, but more often than not the code will be unusable, and occasionally it will have grotesque practices like unused function parameters in it. As far as I can tell we are nowhere near an LLM capable of generating ethical code.