Re:Ornith-1.5: From Self-Scaffolding to Self-Improvement
by xscott on Wednesday August 19, 2026 @05:34PM
(#49367501)
People over-quantize things, muck with the temperature and other settings based on superstitions or results from models they think are similar. There's lots of ways to make 3.8 27B dumber.
[ Parent
| on HN ]
Re:Ornith-1.5: From Self-Scaffolding to Self-Improvement
by razster on Thursday August 20, 2026 @01:37AM
(#49370746)
I've had great success with allowing the model to review optimal settings and my system specs. It comes up with the right configuration. Running Pi harness.
I just had Ornith 1.5 take a moment to configure itself, now it's reviewing a large project I'm working on, so far its really impressive for my needs. Qwen3.8 27b Unsloth(Dynamic 3.0) is also perfect. These two are working together, and I'm in a sweet-spot, I now have all I need.