The experiments that read raw weights and the ones that fix Qwen use completely different techniques.
Rikiya Takehi on Twitter / X
We asked GPT-6 Astra to edit Qwen3.5-0.8B weights to improve math.It directly changed only 0.016% of weights, fixing 0.8B's reasoning loops & improving math up to 6x and even instruction following 3x, without gradients or training.We call this Weight-Space Programming:… pic.twitter.com/DwTwzXzSbE— Rikiya Takehi (@rikiyatakehi) November 2, 2026
Qwenputer: a fully functioning, deterministic RISC-V CPU inside Qwen3.5
I compiled a RISC-V CPU into Qwen 3.5 4B's weights, using its Gated DeltaNet layers as RAM. It runs C and MicroPython inside the forward passes, and Qwen uses it for exact arithmetic.
Qwen on Twitter / X
📢Meet Qwen3.8-Max — our most capable model to date. Next week, the open weights of Qwen3.8-Max will be released, and Qwen3.8-27B is also going open-weights to meet you all!🎉Qwen3.8-Max, a new bar for coding and cowork at 2.4T parameters:- Autonomous coding: 10+ days of… pic.twitter.com/e3YFj2hqcT— Qwen (@Alibaba_Qwen) August 3, 2026
Qwen 3 offers a case study in how to effectively release a model
Alibaba’s Qwen team released the hotly anticipated Qwen 3 model family today. The Qwen models are already some of the best open weight models—Apache 2.0 licensed and with a variety …
Qwen 3.8 27B on my laptop can interpret model weights, too
Yesterday’s hot paper was Sparks of Weight-Space Programming: LLMs can natively read & write neural network weights by Rikiya Takehi, Jayden Teoh, Alex Zhang, and Omar Khattab. The paper found …
Something is afoot in the land of Qwen
I’m behind on writing about Qwen 3.5, a truly remarkable family of open weight models released by Alibaba’s Qwen team over the past few weeks. I’m hoping that the 3.5 …
Astra for Coding: Why Are We Doing This Again?
Some thoughts on Astra and newfangled long-horizon models.
Awni Hannun on Twitter / X
A big jump in intelligence-per-watt today:"Qwen3.5-35B-A3B now surpasses Qwen3-235B-A22B-2507" https://t.co/60j6MviYXY— Awni Hannun (@awnihannun) February 24, 2026
AI Assistant Tool QED Scores bioRxiv Preprint Quality | The Scientist
QED, an AI assistant tool, evaluates the originality and validity of bioRxiv preprints, assigning them QED Scores. Researchers report that its rankings often align with expert opinion.
Qwen on Twitter / X
Qwen3.8 is launching and going open-weight soon!🌐With a massive 2.4T parameters, this model is continuously evolving. We believe it’s one of the most powerful model available today, compatible to leading frontier AI models , second only to Fable 5.You don't have to wait to… pic.twitter.com/JS3ID73IYS— Qwen (@Alibaba_Qwen) July 19, 2026
Local Qwen isn't a worse Opus, it's a different tool
We've all heard people say that Qwen is near-Opus level, but I have receipts and am here to be transparent with you.
Sparks of Weight-Space Programming: LLMs can natively read & write neural network weights
We find that frontier LLMs are surprisingly good at natively reading and writing neural network weights, well past what we’d expect from humans or conventional algorithms.
A 30B Qwen Model Walks Into a Raspberry Pi… and Runs in Real Time
ByteShape's device-optimized release of Qwen3-30B-A3B-Instruct-2507.
How Open Weights Are Changing the AI Race | Serverless Guru
Open Weight models: what they are, why you should care, and how the work of the open-source fine-tuning community around those models is reshaping daily life, both for developers and for everyday AI users.
Astra Is Hard to Monitor
OpenAI’s central message on Astra is that it is three things:
