@no_stp_on_snek: the cleanest thing the RL bought at 9B wasn't intelligence, it was efficiency. Ornith-9B lands the same answers in ~56%…

X AI KOLs Following Models

Summary

Ornith-9B demonstrates that RL training at 9B parameters primarily buys efficiency, achieving same answers with ~56% of the tokens and twice the speed of its base model, offering real cost savings for per-token payment.

the cleanest thing the RL bought at 9B wasn't intelligence, it was efficiency. Ornith-9B lands the same answers in ~56% of teh tokens its base needs (1,299 vs 2,312 per turn) and retries half as often. same destination, way less wandering, roughly 2x faster wall-clock. if you pay per token, that's the headline.
Original Article
View Cached Full Text

Cached at: 06/29/26, 10:34 AM

the cleanest thing the RL bought at 9B wasn’t intelligence, it was efficiency. Ornith-9B lands the same answers in ~56% of teh tokens its base needs (1,299 vs 2,312 per turn) and retries half as often. same destination, way less wandering, roughly 2x faster wall-clock. if you pay per token, that’s the headline.

Tom Turney (@no_stp_on_snek): verdict up front: it’s a “pass” in my book in certain categories, just a narrower one than the 35B. you’re buying real efficiency and sustained-coding coherence here, not a clean across-the-board upgrade over the base.

ran the same skeptic battery on Ornith-1.0’s little brother,

Similar Articles