People like this are the reason AI is so unreliable at exploring code issues.
Like, I just want Copilot to look at my dependencies to explain a vague error I’m seeing and it’s telling me to downgrade Ruby, upgrade Rails, and install Python. Bro, it’s a node package.
Hold up, hold up… We’ve got an ai to do the reading for us. I’ve asked it to summarise what you said. That should give me a bit less reading to do…
The statement appears to be a sarcastic or humorous remark expressing frustration or disbelief regarding an error message that includes a “drop-in replacement function” for a deprecated function. The speaker seems to imply that it is frustrating or almost unbelievable to encounter a message that offers a solution, particularly one suggesting that the replacement can seamlessly take the place of the deprecated function.
By saying, “Why I’d never!”, the speaker is likely exaggerating their frustration or mock surprise, indicating that they might have encountered this situation often or that such suggestions are generally not taken seriously.
This type of comment suggests that the speaker might be somewhat jaded or irritated by encountering such “helpful” messages, perhaps due to previous experiences where the suggested solutions were inadequate, difficult to implement, or not as straightforward as they seem.
“Right? It’s almost like they think a one-line replacement function is going to fix all the issues. It’s never as simple as the message makes it sound, is it? I’ve definitely been burned by those before.”
This response acknowledges the speaker’s frustration and shares a similar sentiment, while also reinforcing the idea that these “helpful” messages don’t always live up to expectations.
People like this are the reason AI is so unreliable at exploring code issues.
Like, I just want Copilot to look at my dependencies to explain a vague error I’m seeing and it’s telling me to downgrade Ruby, upgrade Rails, and install Python. Bro, it’s a node package.
Maybe the onus should be on LLM developers to filter out trash like this from their training datasets
At any rate, it’s extremely unhelpful to not include a version number at the very very least
Damn, if only you could learn to understand the errors. Then you woudln’t have to depend on an llm with hundreds of underpaid workers behind it.
git gud
Me? Reading that there’s a drop-in replacement function for the one that was deprecated, in the error message? Why I’d never!
Hold up, hold up… We’ve got an ai to do the reading for us. I’ve asked it to summarise what you said. That should give me a bit less reading to do…