Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

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

alvins82.github.io

Post reply on HN
Print view View original

21–30 of 74 posts

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

#21

Post by alvins82 »

Btw in my quest for a good desktop codex/claude like app - https://github.com/openchamber/openchamber - this seems to be front-runner. I pair it with OMP via https://github.com/alvins82/omp-openchamber-server/.

I wanted a powerful GUI+harness setup for open models so I could use/test as they came out.

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

#22

Post by rao-v »

onion2k wrote: 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…

Really appreciate this perspective. It’s tempting to stop at being amazed at what these models can do, but my experience matches yours - they need help with details to do well.

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

#23

Post by mcrk »

alvins82 wrote: post #19
poilcn wrote: post #11

Nice. But these tests raise a question what results are reproducible, the final visual, time, tool calling or it's mostly noise. Like, have you tried same combination or model and harness multiple times?

I have on Qwen3.8 27B. Results are close enough across multiple runs.

So it's not reproducible.

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

#24

Post by SadErn »

onion2k wrote: 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…

[dead]

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

#25

Post by pprotas »

alvins82 wrote: post #21

Btw in my quest for a good desktop codex/claude like app - https://github.com/openchamber/openchamber - this seems to be front-runner. I pair it with OMP via https://github.com/alvins82/omp-openchamber-server/ . I wanted a powerful GUI+harness setup for open models so I could use/test as they came out.

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.

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

#27

Post by alvins82 »

pprotas wrote: post #25
alvins82 wrote: post #21

Btw in my quest for a good desktop codex/claude like app - https://github.com/openchamber/openchamber - this seems to be front-runner. I pair it with OMP via https://github.com/alvins82/omp-openchamber-server/ . I wanted a powerful GUI+harness setup for open models so I could use/test as they came out.

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 did try this - I found it overly dev focused - e.g. git +/- changes in left sidebar. I wanted something close to what I am use to with Codex/Claude - just for open models.
Post reply on HN