You can hardly get online these days without hearing some AI booster talk about how AI coding is going to replace human programmers. AI code is absolutely up to production quality! Also, you’re all…
Stack overflow resulted in people with highly specialised examples that wouldn’t suit your application. It’s easier to just ask an AI to write a simple loop for you whenever you forget a bit of syntax
You’ve inadvertently pointed out the exact problem: LLM approaches can (unreliably) manage boilerplate and basic stuff but fail at anything more advanced, and by handling the basic stuff they give people false confidence that leads to them submitting slop (that gets rejected) to open source projects. LLMs, as the linked pivot-to-ai post explains, aren’t even at the level of occasionally making decent open source contributions.
Man i remember eclipse doing code completion for for loops and other common snippets in like 2005. LLM riders don’t even seem to know what tools have been in use for decades and think using an LLM for these things is somehow revolutionary.
the promptfondlers that make their way into our threads sometimes try to brag about how the LLM is the only way to do basic editor tasks, like wrapping symbols in brackets or diffing logs. it’s incredible every time
yep, I came up with promptfans (as a reference for describing all the weirdos who do free PR and hype work for this shit), and then @skillsissuer came up with promptfondlers for describing those that do this kind of bullshit
(and promptfuckers has become to collective noun I think of for all of them)
Stack overflow resulted in people with highly specialised examples that wouldn’t suit your application. It’s easier to just ask an AI to write a simple loop for you whenever you forget a bit of syntax
wow imagine needing to understand the code you’re dealing with and not just copypasting a bunch of shit around
reading documentation and source code must be an excruciating amount of exercise for your poor brain - it has to even do something! poor thing
You’ve inadvertently pointed out the exact problem: LLM approaches can (unreliably) manage boilerplate and basic stuff but fail at anything more advanced, and by handling the basic stuff they give people false confidence that leads to them submitting slop (that gets rejected) to open source projects. LLMs, as the linked pivot-to-ai post explains, aren’t even at the level of occasionally making decent open source contributions.
Man i remember eclipse doing code completion for for loops and other common snippets in like 2005. LLM riders don’t even seem to know what tools have been in use for decades and think using an LLM for these things is somehow revolutionary.
the promptfondlers that make their way into our threads sometimes try to brag about how the LLM is the only way to do basic editor tasks, like wrapping symbols in brackets or diffing logs. it’s incredible every time
Promptfondlers 🤣
yep, I came up with
promptfans(as a reference for describing all the weirdos who do free PR and hype work for this shit), and then @skillsissuer came up withpromptfondlersfor describing those that do this kind of bullshit(and
promptfuckershas become to collective noun I think of for all of them)Air so polluted it makes people sick, but it’s all worth it because you can’t be arsed to remember the syntax of a for loop.