I’m using it as a technical editor for a book I’m writing on bash for beginner programmers. Compiling this book from scratch is a one-man operation; I don’t have the budget or time to hire a technically-competent bash programmer who is also willing to act as a proofreader and editor.
Instead, I plug in certain paragraphs and ask “Does the following paragraph about file descriptors / environment vs. shell variables / fork vs. exec contain any technical errors? If so, please tell me what errors there are, and also provide a more correct alternative statement.” I take what I learn from the output and verify it on a site like StackOverflow.
This has proven to be an effective alternative to starting directly with StackOverflow. Oftentimes I find that “I don’t know what I don’t know”, and am therefore unable to phrase a certain question in a way which is suitable for StackOverflow’s (very specific) expectations. Usually that’s because the question I want to ask is predicated on a series of assumptions, any one of which could be incorrect (and would therefore result in my question being downvoted and/or closed, since it makes the question itself less-broadly applicable to the average user).
But I can ask ChatGPT that same question, and get a correction in my understanding without the loss of those sweet, sweet internet points. At the very least, what I learn from ChatGPT can help me phrase a question which is more suitable for a public forum like SO.
Instead, I plug in certain paragraphs and ask “Does the following paragraph about file descriptors / environment vs. shell variables / fork vs. exec contain any technical errors? If so, please tell me what errors there are, and also provide a more correct alternative statement.” I take what I learn from the output and verify it on a site like StackOverflow.
This has proven to be an effective alternative to starting directly with StackOverflow. Oftentimes I find that “I don’t know what I don’t know”, and am therefore unable to phrase a certain question in a way which is suitable for StackOverflow’s (very specific) expectations. Usually that’s because the question I want to ask is predicated on a series of assumptions, any one of which could be incorrect (and would therefore result in my question being downvoted and/or closed, since it makes the question itself less-broadly applicable to the average user).
But I can ask ChatGPT that same question, and get a correction in my understanding without the loss of those sweet, sweet internet points. At the very least, what I learn from ChatGPT can help me phrase a question which is more suitable for a public forum like SO.