Microtransactions for devs
-
If you can read the code it writes and modify it, a project manager can remove that time from you and take the AI slop direct to production.
That's a different problem. The original question was when would a competent dev use an LLM.
-
In which case would a competent dev use an LLM?
It's outstanding at bridging the gap between "I need to mash these two concepts/technologies together" and "the answer is spread across six different StackOverflow threads." Hunting that stuff down using Google has been a delicate operation even at the best of times in the last 25 years, but it always took a lot of time. With an LLM and each such query, I've saved hours, maybe even whole workdays. Fact-checking an AI takes far less effort.
-
At this point, this movie is probably older than most of the people that use this meme template.
brb crawling into a hole and crying
-
If you can read the code it writes and modify it, a project manager can remove that time from you and take the AI slop direct to production.
Another good reason to never let the company's project become your project.
-
And you are sure it's not spewing hallucinations or neo-fascism in a language you don't understand... why?
You should try using an LLM to translate things. It's wctually pretty good compared to more traditional translators. I think translation is actually an area LLMs excels in.
-
In which case would a competent dev use an LLM?
Boring, tedious shit that doesn’t require brainpower, just time, when fixing whatever comes out of the LLM is less annoying than doing it myself.
-
I very rarely find result summarizers useful. If I didn't find something normally, there won't be anything in there.
I sure love tests and huge codebases with errors in them. In the time I read and understood an LLM's output, I could write it myself. And save on time later when expanding/debugging.
When yarn/react/next.js/amplify breaks in some new and idiotic way, Claude is helpful more often than not. Why spend hours googling and sifting through github/stack overflow/etc when Claude can tell me what option to tweak to fix it in a fraction of the time?
-
That's a different problem. The original question was when would a competent dev use an LLM.
Which the answer is: never. If they did, by definition they would not be competent (unless they are being specifically trained in how to avoid code slop).
-
You should try using an LLM to translate things. It's wctually pretty good compared to more traditional translators. I think translation is actually an area LLMs excels in.
Why would I do that when I can talk to a human? (or, at least, something in the internet that pretends to be that)
-
Why would I do that when I can talk to a human? (or, at least, something in the internet that pretends to be that)
You've never needed to translate something before? As an example at a grocery store sometimes there are foods with instructions in other languages. Sometimes the entire item is in another language and I want to know what it is.
-
You've never needed to translate something before? As an example at a grocery store sometimes there are foods with instructions in other languages. Sometimes the entire item is in another language and I want to know what it is.
And I'd ask ten people before a machine. If I had to ask a machine, then I'd have to ask 9 people anyway just to verify if the machine answer is any trustable; after all, the entire point is I couldn't do it myself.
