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

Ornith-1.0: self-improving open-source models for agentic coding

github.com

Post reply on HN
Print view View original

61–65 of 65 posts

Re: Ornith-1.0: self-improving open-source models for agentic coding

#63

Post by kamranjon »

nacs wrote: post #60
kamranjon wrote: post #8

Earlier quoted context omitted.

I think the 9b and 31b dense are Gemma models and the 35B-MoE, and 397B-MoE are Qwen models since these are model sizes covered by each of them respectively

Only the 31b is Gemma. All the rest - including 9B - are Qwen 3.5/3.6: https://huggingface.co/deepreinforce-ai/Ornith-1.0-9B/blob/m...

ah yeah you're correct - sorry for the confusion

Re: Ornith-1.0: self-improving open-source models for agentic coding

#64

Post by lhl »

regularfry wrote: post #58
lhl wrote: post #54

I've been testing Ornith-1.0 35B (my own FP8-block quant) and I like it. It runs at >200 tok/s w/ vLLM on an RTX PRO 6000 (sm120), I've run >140M cached tokens of agentic coding work on it over the past few days. It seems to about somewhere between Qwen 3.6 35B-A3B and 27B, but the good thing: it overthinks/doom-loop a lot less than Qwen 3.6. When looking at the thinking traces I like its breakdown approach template.…

With this model size I've found that the harness seems to matter more. I've moved on to little-coder rather than raw pi with qwen3.6 27b personally, it might be worth taking a look.

You got me curious, so I made a little harness comparison to my model test suite:

    Model                              Adapter       Suite           Score   Passed  Tasks
    ---------------------------------  ------------  --------------  ------  ------  -----
    local/ornith-1.0-35b               little_coder  aider_polyglot  36.0%   81/225  225
    local/ornith-1.0-35b               pi_devstack   aider_polyglot  39.6%   89/225  225
    local/ornith-1.0-35b               pi_vanilla    aider_polyglot  32.0%   72/225  225
Little Code does a little better than raw Pi, although maybe not better than my personal Pi setup: https://github.com/lhl/devstack

Re: Ornith-1.0: self-improving open-source models for agentic coding

#65

Post by Iris595 »

GenseeAI wrote: post #57

Self-improving systems are exciting, but they also make provenance and governance much harder. Once agents can modify their own behavior over time, understanding why an agent behaved a certain way becomes increasingly important.

Agree! More and more industry news also raises concerns about how to regulate agent behavior. Any take on possible actions?
Post reply on HN