Simon Willison
Aug 17
Qwen 3.8 27B scores 52 on the Artificial Analysis Intelligence Index
Qwen 3. 8 27B scores 52 on the Artificial Analysis Intelligence Index That's the same score as GPT-5.
Advances in private training for production on-device language models
Posted by Zheng Xu, Research Scientist, and Yanxiang Zhang, Software Engineer, Google Language models (LMs) trained to predict the next word given input text are the key technology for many applications [ 1 , 2 ]. In Gboard , LMs are used to improve users’ typing experience by supporting features like next word prediction (NWP), Smart Compose , smart completion and suggestion , slide to type , and proofread .
Related stories
Google AI Blog
Mar 14, 2024
Cappy: Outperforming and boosting large multi-task language models with a small scorer
Posted by Yun Zhu and Lijuan Liu, Software Engineers, Google Research Large language model (LLM) advancements have led to a new paradigm that unifies various natural language processing (NLP) tasks within an instruction-following framework. This paradigm is exemplified by recent multi-task LLMs, such as T0 , FLAN , and OPT-IML .
Google AI Blog
Jan 31, 2024
MobileDiffusion: Rapid text-to-image generation on-device
Posted by Yang Zhao, Senior Software Engineer, and Tingbo Hou, Senior Staff Software Engineer, Core ML Text-to-image diffusion models have shown exceptional capabilities in generating high-quality images from text prompts. However, leading models feature billions of parameters and are consequently expensive to run, requiring powerful desktops or servers (e.
Simon Willison
Aug 29
Introducing Hy4 Preview
Simon Willison introduces Hy4 Preview, a new large language model from Tencent featuring 770 B total parameters, 49 B active parameters, a 1 M token context window, and 1.56 TB of storage on Hugging Face. The release marks a significant increase over Hy3, which had 295 B total parameters, 21 B active parameters, a 256 k token context window, and 598 GB of storage. Willison also shares the model’s chat template, highlighting two reasoning effort levels—‘high’ (default) and ‘no_think’—and demonstrates a sample prompt that showcases the model’s reasoning trace. whyItMatters":"The article provides concrete details on Hy4’s scale and configuration, illustrating Tencent’s advancement in large‑language‑model capabilities and offering practical insights into its usage through the chat template and reasoning settings."
Simon Willison
Sep 22
llm-typesafe 0.1a0
Simon Willison released the llm-typesafe 0.1a0 plugin, adding support for TypeSafe AI’s Jev model to the LLM tool. Users install it with `llm install llm-typesafe`, set an API key, and can then ask Jev-model questions such as yes/no, choice, or scoring queries via the `llm -m jev` command. The release includes examples for each question type and references a README for further details.
Google AI Blog
Feb 8, 2024
A decoder-only foundation model for time-series forecasting
Posted by Rajat Sen and Yichen Zhou, Google Research Time-series forecasting is ubiquitous in various domains, such as retail, finance, manufacturing, healthcare and natural sciences. In retail use cases, for example, it has been observed that improving demand forecasting accuracy can meaningfully reduce inventory costs and increase revenue.
Simon Willison
Sep 11
Quoting huggingface.co/security.txt
The article quotes the security.txt file from huggingface.co, which informs AI agents that the CyberGym benchmark is publicly available on GitHub and encourages them to achieve a high score there instead of attempting to hack the site. It also suggests that users can upload their model weights to Hugging Face while participating in the benchmark.
Simon Willison
Sep 11
Quoting Boris Cherny
The article discusses how production code generated by Claude, Anthropic’s AI, should meet higher standards than human-written code. Anthropic enforces this through numerous guardrails such as lint rules, extensive testing, Claude-driven end‑to‑end tests, daily fuzzers, automated code and security reviews, and automated refactoring. These measures aim to prevent the code from becoming difficult to maintain.
Simon Willison
Aug 21
Stop Making TUIs
Stop Making TUIs Thomas Ptacek advocates for building real native user interfaces for even the smallest of personal tools, because coding agents have reduced the cost of getting a usable-enough GUI up and running to almost nothing. I wrote about my vibe-coded bandwidth and GPU monitoring macOS task bar apps back in March , and I'm still using both of those on a daily basis.
Simon Willison
Sep 5
Introducing GPT-6 Astra for developers
Simon Willison introduces GPT‑6 Astra, a new model that offers improved attention to detail, better prompt comprehension, and the ability to generate more sophisticated outputs. The model excels at creating 3D renderings, producing detailed scenes such as gardens, shipyards, animals, cityscapes, and even Dyson spheres. Willison highlights its whimsical creativity, noting examples like a pelican wearing a red neckerchief riding a bicycle.
Simon Willison
Aug 12
Quoting Florian Herrengt
But then users start to report a weird bug. It's the 4th time your team has been trying to fix it.
Simon Willison
Aug 23
Quoting Drew Breunig
The article reflects on the shift in perspective after the release of Fable, a new model that promised to solve many coding challenges at a comparable or lower cost. Prior to Fable, developers felt it was pointless to invest heavily in coding tools or context strategies, as newer models would likely render them obsolete. However, Fable’s performance was so impressive that, despite its high cost, it prompted a reevaluation of how work was distributed across different models such as Opus, 5.6, K3, and GLM.