Seminar2250

joined 6 months ago
[–] Seminar2250@awful.systems 9 points 3 weeks ago* (last edited 3 weeks ago) (1 children)

it's democratic if i couldn't do it yesterday but i can do it today, even though it's not the same in any meaningful way

edit: in all seriousness, it's disgusting the way they are pretending there is some noble intention behind any of this.

[–] Seminar2250@awful.systems 5 points 3 weeks ago

i skimmed and it caused psychic damage

would not encourage

[–] Seminar2250@awful.systems 5 points 3 weeks ago

thank you for the suggestion, this is good stuff.

[–] Seminar2250@awful.systems 7 points 3 weeks ago* (last edited 3 weeks ago) (4 children)

oh fuck, i didn't think of that! thank you for the idea 💖

[–] Seminar2250@awful.systems 7 points 3 weeks ago* (last edited 3 weeks ago) (8 children)

i'm trying to sell mine now

but also i don't have any other computers and probably can't afford anything

time for me to learn to use a pencil

[–] Seminar2250@awful.systems 6 points 3 weeks ago (2 children)

you could also just engage in good faith and see if it's an echo chamber

[–] Seminar2250@awful.systems 3 points 3 weeks ago* (last edited 3 weeks ago)

it sounds like you've only used the llm with the anus logo

have you tried this other llm^[https://velvetshark.com/ai-company-logos-that-look-like-buttholes]?

image descriptionpicture of various tech company's logos arranged in the outline of a butt with claude's logo in the center

claude's logo looks like an anus

[–] Seminar2250@awful.systems 3 points 3 weeks ago

"blask" slaps idc what anyone says

[–] Seminar2250@awful.systems 7 points 3 weeks ago* (last edited 3 weeks ago) (2 children)

this comment:

Unless you’ve only ever used ChatGPT, you will know that LLM-produced code is not the result of a single prompt, not even a conversation, but rather a workflow that often goes as such:

  • Discuss a problem with the LLM. The LLM autonomously reads large parts of the repository you’re working in, during the discussion.
  • Ask it to write a plan. Edit the plan. Ask it about the edited plan. Edit it some more.
  • Repeatedly restart the LLM, asking it to code different parts of the plan. Debug the results. Write some code yourself. Create, rebase, or otherwise play around with the repository; keep multiple branches of potential code.
  • Go back and edit the original plan, now that you know what might work. Port some unit tests back in time, sometimes.
  • Repeat until done.

is so stupid

[–] Seminar2250@awful.systems 5 points 3 weeks ago

100% certain this dork has the wikipedia page for logical fallacies open 24/7

view more: ‹ prev next ›