alt Hacker NewsRemember that LLMs are still computer programs, and so are inherently deterministic. A model given the same input multiple times will always produce the same output. The randomness is added on top. This is why LLM-produced text, websites, images all seem so generic.
It's likely that multiple agents doing a certain task all independently thought "let me try writing on this website".
Replies
leodavi • yesterday at 3:35 PM
What? No. Have you ever worked with programs that do floating-point math on a GPU? It's not deterministic, definitely across platforms, and often within a single platform, too.
➕ show 1 reply
> This is why LLM-produced text, websites, images all seem so generic.
No, it is not why. That's not inherent to the LLM architecture at all but appears after RL training. Base models don't have any problems with genericness.