k
keynews.ai
keynews.ai
FrontierThe story, in brief

Orthrus-Qwen3: up to 7.8×tokens/forward on Qwen3, identical output distribution

7.8×. That's the token throughput gain Orthrus just unlocked on Qwen3—without changing a single output.

Reporting by Hacker News 1 min brief
Illustration of a transparent lens revealing connected networks across layers of paper.
Exploring the next frontier of AI research.AI illustration by KeyNews
The KeyNews take

Why it matters

Open-source optimization technique demonstrates dramatic inference efficiency improvements on frontier models. Relevant for teams operating under compute constraints and evaluating cost-per-inference at scale.

The key facts

10 to know

  1. 7.8× tokens/forward throughput improvement

  2. Maintains identical output distribution (no accuracy loss)

  3. Works on Qwen3 model

  4. Open-source implementation (GitHub)

  5. 49 points on Hacker News (moderate traction)

  6. 7.8× tokens/forward improvement claimed on Qwen3

  7. Identical output distribution preserved (no quality degradation)

  8. Published as open-source GitHub repo

  9. Early-stage community validation (49 HN points, 3 comments as of publication)

  10. Date: May 15, 2026 (future date—verify publication authenticity)

Go to the source

Hacker Newsgithub.com

Publisher excerpt: Article URL: Comments URL: Points: 49 # Comments: 3
Read original report
Back to today's editionMore frontier news

The wider picture

View all
Illustration of a transparent lens revealing connected networks across layers of paper.
AI illustration by KeyNews
Frontier01

Alibaba Unveils Zhenwu V900 — and Plans Qwen Models With Up to 10 Trillion Parameters

Alibaba is advancing on two fronts simultaneously: announcing a custom AI accelerator (Zhenwu V900) and committing to massive model scale (10T parameters for future Qwen releases). For practitioners, this matters as a credible third-party capability play outside the US-China licensing squeeze; for enthusiasts, it's a significant lab-race signal about training compute and parameter scaling as competitive levers.

TechRepublic
Illustration of a transparent lens revealing connected networks across layers of paper.
AI illustration by KeyNews
Frontier02

Kyutai Releases Voice of Reason: A Speech-Native Model that Solves Spoken Math with Reinforcement Learning

A new capability frontier: models that reason directly in speech without transcription bottlenecks. This changes how we think about multimodal reasoning and what's possible with open-weight releases at scale.

MarkTechPost
Illustration of a transparent lens revealing connected networks across layers of paper.
AI illustration by KeyNews
Frontier03

Claude Opus 5.5, GPT-6 Sol, GPT-6 Luna, and a new price war

Frontier labs are shipping upgraded reasoning and multimodal models in rapid succession, signaling acceleration in the capability race. Simultaneous price cuts reshape AI economics for practitioners.

Simon Willison