HNHacker News
TopNewBestAskShowJobs

alvins82

52 karma · joined August 30, 2024

submissionscomments
alvins82··on I tested 10 model/harness combinations on the same Three.js task
Added costs
alvins82··on I tested 10 model/harness combinations on the same Three.js task
Added costs.
alvins82··on I tested 10 model/harness combinations on the same Three.js task
Added costs.
alvins82··on I tested 10 model/harness combinations on the same Three.js task
Added costs.
alvins82··on I tested 10 model/harness combinations on the same Three.js task
I have posted all the transcripts on github so you can point your AI at it and prompt away. https://github.com/alvins82/hangar-harness-model-tests/
alvins82··on I tested 10 model/harness combinations on the same Three.js task
Deepseek Harness. PTC is one of the 'modes' it has.
alvins82··on I tested 10 model/harness combinations on the same Three.js task
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.
alvins82··on I tested 10 model/harness combinations on the same Three.js task
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.

alvins82··on I tested 10 model/harness combinations on the same Three.js task
I have done multiple runs on Qwen3.8 27B. Results are close enough across multiple runs qualitatively.
alvins82··on I tested 10 model/harness combinations on the same Three.js task
I have on Qwen3.8 27B. Results are close enough across multiple runs.
alvins82··on I tested 10 model/harness combinations on the same Three.js task
Why not ohmypi?
alvins82··on I tested 10 model/harness combinations on the same Three.js task
I've just pushed the transcripts of each if that helps. https://github.com/alvins82/hangar-harness-model-tests
alvins82··on I tested 10 model/harness combinations on the same Three.js task
Interesting also that Astra and Sol didn't check visually using the browser. I suspect they would have done even better if they had.