Live data from Hacker News

I tested 10 model/harness combinations on the same Three.js task

alvins82.github.io

61–70 of 84 posts

Re: I tested 10 model/harness combinations on the same Three.js task

#61
post #14

The Astra version seems to have used three.js r170, which is from October 2024. Sol used an even earlier version. GLM's code used the latest version, but I think it's just getting three.js@latest from jsdelivr so it's unlikely to be writing code against that version. Qwen on OpenCode also fetches from jsdelivr, but using a pinned version at r160. I don't think any of these examples are using things like tone mapping…

The fact that these tools are capable of doing anything at all is a miracle to me.

Re: I tested 10 model/harness combinations on the same Three.js task

#65
post #56
post #25

Earlier quoted context omitted.

I like Paseo https://github.com/getpaseo/paseo But I am annoyed at these GUIs implementing features I don’t care about. I want them to just wrap my harness and forward it to my iPhone, but they can’t help themselves from feature creep.

i liked paseo too but its not optimized at all. let alone the feature bloat.

What do you use then?

Re: I tested 10 model/harness combinations on the same Three.js task

#67
post #14

The Astra version seems to have used three.js r170, which is from October 2024. Sol used an even earlier version. GLM's code used the latest version, but I think it's just getting three.js@latest from jsdelivr so it's unlikely to be writing code against that version. Qwen on OpenCode also fetches from jsdelivr, but using a pinned version at r160. I don't think any of these examples are using things like tone mapping…

The fact that these tools are capable of doing anything at all is a miracle to me.

How am I driving? How does an engine even work?

Re: I tested 10 model/harness combinations on the same Three.js task

#70
post #7

It’s really interesting how much little choices make the result better or worse. Astra and one of the GLMs added bright lights, and thus looked so much better to my eye. Genuinely happy with some of the Qwen 3.8 results (especially since I can run that model at Q8). Interesting to see how much better (at this task) Pi (OMP) is over Opencode as a harness. I’d love to see a few more with outcomes that are as easy to ju…

Yeah, most of them made it too dark to see what's going on.

Also your last paragraph sounds like the setup for a late 80s scifi movie...

Post reply on HN