alvins82

Joined 2 years ago

Karma

52

Submissions

16

Member since

Aug 30

View on Hacker News

Recent submissions

Comment · 1 month ago

Comment · 1 month ago

Comment · 1 month ago

Comment · 1 month ago

Comment · 1 month ago

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/

Comment · 1 month ago

Deepseek Harness. PTC is one of the 'modes' it has.

Comment · 1 month ago

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.

Comment · 1 month ago

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.

Comment · 1 month ago

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

Comment · 1 month ago

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

Comment · 1 month ago

Why not ohmypi?

Comment · 1 month ago

I've just pushed the transcripts of each if that helps. https://github.com/alvins82/hangar-harness-model-tests

Comment · 1 month ago

Interesting also that Astra and Sol didn't check visually using the browser. I suspect they would have done even better if they had.