Hacker News Reader

Comment by rep_lodsb | Hacker News Reader

>[I]f you're a teacher and you have a student named David Mayer and you want help sorting a class list, ChatGPT would refuse the task.

Maybe use the right tool for the job? Just kidding, of course LLMsort will soon be in standard libraries.

View on HN

This is perhaps a too extreme example and I wouldn't use ChatGPT for sorting a class list when it's trivial to do in a spreadsheet, especially because I'll probably need to have the list stored as a spreadsheet anyway to keep track of grades. However, from a more general point of view, there is value in having a universal interface that you can use to perform a huge variety of tasks, including also tasks for which it is clearly overkill.

Using the right tool for the job means knowing what the right tool is, having it installed (or getting access to it), knowing how to use it, opening it and having one more window/tab to context-switch to and from, etc.

Outsourcing tasks to an LLM that can be solved in traditional task-specific ways is extremely inefficient in various ways (cost, energy consumption, etc.) but it makes sense to save human time and effort... as long as it's for tasks that LLMs can actually do reliably, of course.

It'll come as an npm package which will download 30GB model.

Don’t start blaming JS people for this AI mess! We’re busy making webpages slow.

And draining battery with electron apps , our work is important driver of new laptop sales and boosts the economy

For a non developer, an LLM interface is absolutely the right tool for this job.

"Mr. Smith, why didn't you just sort -o students.txt students.txt. Are you stupid?" (Not to mention that real data is messy, and requires pre & post processing)

LLMs are access to computation for people whose "standard library" is a quiet old building downtown.

"i would be happy to assist you in rtfm"

Excel. Most likely the student info is in a spreadsheet already anyway. Everything outside of tech runs on Excel.

If someone doesn't have the skills to parse text programmatically, the situation can often be something like "a Word table of names in a 4-wide grid with random missing fields, spanning three different pages, one of which is no longer a true table because it was copied out and pasted in again from a messenger chat someone sent last year", and LLMs can be quite good for one-off tasks like that. Definitely good enough that people will keep using them like that, at least.

Yeah, chatgpt is great for text manipulation. I used it to format a list I copied from Wikipedia then had it write a script to rename a bunch of videos using that list.

"AI Bubble Sort" surely?

bozo sort would be oddly redundant

Bonzi Buddy Reloaded

What’s amazing is that if you install and run BonziBuddy (in a Win98 or XP VM, ofc) is his little RAM the whole thing uses - despite being blatant spyware.

There used to be a care for the craftsmanship, I tell you! :b

No kidding, I recently tried to use Copilot to generate a list of methods in a class, grouped by access (public/private/protected) and sorted by number of lines. And it was not possible! It duly generated lists upon lists, but all of them had mistakes, some of them obvious (like all private methods having the same number of lines), some less obvious.

The relevant xkcd is https://www.xkcd.com/1185/

The implementation of stack sort is https://github.com/gkoberger/stacksort/ and hosted on https://gkoberger.github.io/stacksort/

write a story with all the students in my class (list of names) going on an exciting dungeons and dragons like adventure!

Didn't you already make this exact same joke on another LLM post?

Reply on news.ycombinator.com