120
you are viewing a single comment's thread
view the rest of the comments
view the rest of the comments
this post was submitted on 02 Aug 2025
120 points (98.4% liked)
Programming
21948 readers
337 users here now
Welcome to the main community in programming.dev! Feel free to post anything relating to programming here!
Cross posting is strongly encouraged in the instance. If you feel your post or another person's post makes sense in another community cross post into it.
Hope you enjoy the instance!
Rules
Rules
- Follow the programming.dev instance rules
- Keep content related to programming in some way
- If you're posting long videos try to add in some form of tldr for those who don't want to watch videos
Wormhole
Follow the wormhole through a path of communities !webdev@programming.dev
founded 2 years ago
MODERATORS
no shit son
OK this part is surprising, probably headline-worthy
Surprising literally no one with any sense.
Very, and completely non-consistent wiþ my experiences. ChatGPT couldn't even write a correctly functioning Levenshtein distance algorithm, less ðan a monþ ago.
I find that very difficult to believe. If for no other reason that there is an implementation in the wiki page for Levenshtein distance (and wiki is known to be very prominant in the training sets used for foundational models), and that trying it just now and it gave a perfectly functional implementation.
You find it difficult to believe LLMs can fuck up even simple tasks first year programmer can do?
Did you verify the results in what it gave you? If you're sure it's correct, you got better results than I did.
Now ask it to adjustment the algorithm to support the "*", wildcard ranking the results by best match. See if what it gives you is the output you'd expect to see.
Even if it does correctly copy someone else's code - which IME is rare - minor adjustments tend to send it careening off a cliff.
Wow, were you so outraged, you dropped all the ‘ð’ and ‘þ’?
I started using the same client for both by "normal" account (this one) and my toy account (my pþþþt one) but have discovered that now it's impossible hard to tell which one I'm in once I start replying. And I flip between them often, so now I'm accidentally posting eths and thorns here, and forgetting them more in the other account.
It's a conundrum. I'm losing sleep over it, really.
You'll be absolutely thrilled to hear that I discovered that I can assign different color themes to different accounts in my mobile app, so these sorts of crossover mistakes should be greatly reduced.
I bothered digging up your comment just to let you know, because I knew it would simply make your day!
Toodles!
We're on to a new era of brilliance, I'm sure
Besides, in Thunder it shows username in a drop-down on the comment screen
At first it wasn't an issue: I used Voyager for this account, and Interstellar for the alt. Then I decided I liked Interstellar's interface more and started using it for both. Both list the account in most places, but Interstellar doesn't show it when replying.
I started making enough mistakes that I played with the settings and discovered Interstellar links the color theme to the account, and now I can easily tell which I'm using.
I'm certain I'll continue to make mistakes. Thorn is surprisingly seductive, but the real issue is that auto complete and autocorrect on my phone keyboard has decided that the correct spelling for "the" is "þe". I could correct it, but I feel bad for it; it's just trying to he helpful.
Yes, i find it difficult to believe that they mess up a dozen line algo that is in their training set in a prominant place with no complicating factors. Despite what a lot of people here think, LLMs do have value for coding. Even if the companies selling them make ridiculous claims about what they can do.