Comment on Coinbase CEO explains why he fired engineers who didn’t try AI immediately
Quibblekrust@thelemmy.club 1 day agoAnd most devs I know use it everyday, so… 🤷
Especially for repetitive mundane code, like they said. It’s much faster to check code for correctness than it is to write it in the first place.
“I need to restructure this directory tree. If a file has “index” in the name, then it has to go in a parallel directory structure starting at “/home/repos/project/indexes/” with the same child folders as the original.”
There, I just finished a custom Python script to accomplish that. Can I do it myself? Yes. Can I do it in 30 seconds? No. Why would I waste my time writing such a mundane script for a one-off thing?
This is what LSPs are for, or even like just a baseline knowledge of CLI tooling (honestly, like, just mv and sed)
. You do not need an LLM for any of what you’ve described, and I would argue that I can probably do it faster by hand than you can prompt your LLM and debug the slop it hands you back.
It was just a contrived example for the purpose of the comment, and I admit it wasn’t a good one.
How about turning a directory tree of dozens of .url files (Windows web shortcut files) into an HTML file? Directory names as section headings, and nested bulleted lists of hrefs using the .url file names as the link text, minus the “.url”. Can you do that on the CLI? Sure, but it would be a hell of a hack. It would be a disgusting blob of awk code, probably. You’re much better off writing it in something like Python.
It’s not hard stuff. It’s simple directory recursion, string building, and file writing. It’s just so mind-numbingly boring to write, and it takes time. Instead, Copilot made that for me in 10 seconds. As fast as I could articulate the need in text. No debugging needed. Worked the first time. All I had to ask for in a second pass was more indenting of each nested list, and I could have just added that myself.
I would argue that I can probably do it faster by hand than you can prompt your LLM and debug the slop it hands you back.
It’s funny that you’re not even sure you can do that extremely simple thing in my original comment faster than I could prompt an LLM. And your prejudice is showing by assuming I had to even debug it, or that the code was slop. The code looked great. It was perfect Python.
I wish all of you people would stop knocking what you’ve never even tried. Because it just makes you sound bigoted, using words like “slop” and making assumptions about the quality of the output while never having tried it yourself. Prejudice is never a good thing.
I’ve written a fair amount of advanced command line stuff using grep and sed and whatever else. Anything non-trivial takes just as much debugging as Python code, and it’s harder to read and debug. And when it’s boring, one-off code, why would you even want to do it yourself?
I’ll never understand the LLM hate on lemmy. Feel free to hate on capitalism, or on using fossil fuels to power LLMs, or on having no social safety net when LLMs displace jobs, or any number of other things, but to be prejudiced and assume it’s always slop when you’ve never even tried it just makes no sense to me. It’s a revolutionary tool in its infancy, and it’s already very useful on certain tasks.
It’s funny that you’re not even sure you can do that extremely simple thing in my original comment faster than I could prompt an LLM.
No, see, this is called “having integrity” by not asserting as fact a hypothetical. I am 100% certain that I could knock out your hypothetical in one command in less than a minute but since I didn’t go actually do it I didn’t pretend that I did.
I do love the whole “oh but it knocks out all of the mundane stuff” as if that’s the primary part of our job. I have been doing development for about 30 years and I have spent so little time on mundane tedious tasks in that time. Certainly not enough time to justify the ecological impact of LLM data centers (even if they actually worked as well as advocates claim).
I wish all of you people would stop knocking what you’ve never even tried.
This is your prejudice showing (the only way someone would not like this is if they haven’t tried it). I have tried it, and I found it to be a waste of my time. What I saw was a stochastic parrot providing me objectively wrong answers to questions and code that I needed to completely rewrite before it would function as advertised.
That product is not worth drinking the worlds water and ruining people’s quality of life near data centers over. It’s not worth the theft of IP and original thoughts, the obvious copyright violations as it crawls the web (ignoring every standard “do not crawl” marker I know of), the extra cost to site hosts as LLMs savagely barrage their pages. It’s not worth lining the pockets of already super rich VCs as they exploit blockchain 2.0 until the bubble bursts. It’s not worth the real human beings who have already lost their livelihood because an executive is frothing at the mouth to replace people with machines and has been promised AGI “any day now” by LLM spokespeople who don’t seem to understand that whole integrity thing above.
The hate that you see might have something to do with the willingness to ignore all of the above so “save some time” on the alleged “mundane tasks” people seem to think dominates the industry.
It’s a revolutionary tool in its infancy, and it’s already very useful on certain tasks.
That’s a bold and premature statement IMO, how many AI winters have there been before this one ?
I’m not even saying you’re wrong, but to assert it with such confidence sounds like crypto bro-nanigans.
i would argue that it’s evolutionary rather than revolutionary, but that’s subjective i suppose.
I’ll never understand the LLM hate on lemmy.
Speaking for me personally i don’t hate LLM’s i dislike the confidence with which they are being pushed and the lack of acknowledgement of their limitations.
You get statements like
“And most devs I know use it everyday”
Without context, and that feeds into the general propaganda feel of the sentiment, because people who don’t actually use them or don’t understand the implied context hear “LLM’s can do all the things, all the professional devs are using it all day”.
I understand it’s not on you to police peoples impressions, but trying to add actual context to those statements isn’t hate, it’s prudence.
Then again, that’s subjective too.
Now re-explain this 5 more times before it shits out something remotely close to what you’re asking it to do.
That hasn’t been my experience for something this simple. Not at all. I vibe coded a 75 line Python script the other day and it worked perfectly the first try.
everyday
“every day”, if you mean ‘daily’.
Senal@programming.dev 1 day ago
In certain circumstances sure, but at any level of complexity, not so much.
At some point it becomes less about code correctness and more about logical correctness, which requires contextual domain understanding.
Want to churn out directory changing python scripts, go nuts.
Want to add business logic that isn’t a single discrete change to an existing system, less likely.
For small things is works OK, it’s less useful the more complex the task.