Yes! The bonus materials include training on the Project Gutenberg public domain book corpus. I don’t want to go beyond that though and curate other datasets because of copyright concerns. However, you could eg use the FineWeb dataset which is available from hugging face.
LLMS
-
Reinforcement Pre-training Already Explored in Earlier Research
By
–
Have to look into this one more, but it’s already been a thing; eg “Reinforcement Pre-training” from earlier this summer
-
Missing Comparisons with GPT-5-Codex and Gemini 2.5 Pro Models
By
–
Hard to tell given that comparisons with gpt5-codex and gemini-2.5-pro etc are missing
-

OpenAI Launches Compute-Intensive Pro Models for Scientific Research
By
–
OpenAI will release numerous new, pro-tier, compute-intensive models – in the coming weeks. I am incredibly excited. My guess is that at least one model will be dedicated to scientific research, biology, chemistry, and physics research. This is a focus of AI that is emphasized
-
Qwn3-Max: Large Closed-Weights Model Analysis
By
–
Note: Qwn3-Max is not open weights and is quite large (and seemingly expensive) model.
-

Qwen3-Max Impresses as Non-Reasoning Model
By
–
So far, Qwen3-Max seems impressive for a non-reasoning model, doing a good job at a lot of my weird tests that even some reasoners struggle with.
-

China’s New Frontier Lab: Alibaba’s Tongyi and Qwen-Max Models
By
–
China has a new frontier lab, and it's Tongyi ("all in one").
— swyx 🐣 (@swyx) 24 septembre 2025
in case you were wondering why @JustinLin610 was in such a mad dash to ship so many models, including the monster 1T param Qwen-Max, it's because the Alibaba Cloud conference just happened and they laid out their… https://t.co/andUOFoN23 pic.twitter.com/UlcHBZGm11China has a new frontier lab, and it's Tongyi ("all in one"). in case you were wondering why @JustinLin610 was in such a mad dash to ship so many models, including the monster 1T param Qwen-Max, it's because the Alibaba Cloud conference just happened and they laid out their
-
Model Limitations: Why AI Cannot Generate Ungrounded Content
By
–
That would be a model that couldn't answer the prompt "write me a story where a walrus teaches me the basic ideas of particle physics" Because a Walrus never said those things!
-

Alibaba Releases Qwen3-Omni Multimodal AI Model
By
–
China will always stay one step ahead of the U.S. in AI Alibaba just dropped Qwen3-Omni and it's the first model that doesn't sacrifice anything to be multimodal. Usually when you add vision and audio to a language model, text performance tanks. Not here. Qwen3-Omni-30B-A3B