Hacker News Reader

Comment by Kayou | Hacker News Reader

Why do all LLMs do a particle simulation when you ask them this prompt ? Qwen3.6, Qwen3.8 and Ling 3.0 Tiny all did the same thing !

I find Ling 3.0 tiny particularly interesting as it looks really nice for a tiny model with 7.9B total parameters, with only 1.3B parameters activated per token. Here is the result https://coolthing-ling-3-tiny.tiiny.site (sorry for the weird hosting, first I found that worked)

(it cost me almost 0 cents and done in 49 seconds)

View on HN

> Why do all LLMs do a particle simulation when you ask them this prompt ? Qwen3.6, Qwen3.8 and Ling 3.0 Tiny all did the same thing !

Datasets contains lots of people sharing particles simulations in various ways, with a bunch of people replying "that's so cool" and similar, so 10 years later someone asks an LLM for "cool thing" and "particle simulations" rank pretty far up when it thinks about what others have called cool.

There is that, but RLHF is a stronger influence. People who asked to build a cool HTML and JavaScript thing, or things of that sort were more pleased to see working shaders and other cool visual effects that are obscure to create (for most). That gets fed back as a reward.

Also the reason LLMs are positive, enchanting, pleasant, glorifying, demagogues.

Not because it's skewed tone in the data. They are acute politicians.

Add Opus 5.0 to your list. (GPT 5.6 Terra tried to give me some kind of driving-at-night-with-a-starfield thing, but failed quite hard).

Reply on news.ycombinator.com