Simon Willison
5d ago
pwasm 0.2a0
Release: pwasm 0.2a0 pwasm is one of my folly projects - an entirely vibe-coded pure Python WebAssembly engine that I built in January during my first bout of AI mania. I hadn't touched it sin...
Introducing Muse Glimmer
Introducing Muse Glimmer Meta are back in the open weights game! Muse Glimmer is a brand new 30B model under a clean Apache 2.
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 .
Simon Willison
Aug 9
GitHub Models is now retired
GitHub Models is now retired I missed this news until today, when the GitHub Actions run for my simonw/research repository failed with this error message: GitHub Models is temporarily unavailable as part of a scheduled retirement brownout. That message is already stale, because the retirement has been completed.
Simon Willison
6d ago
Quoting Anthropic Frontier Red Team
The article reports that on a set of 100 randomly selected tasks from an internal Binary Exploitation benchmark, GLM‑5.3 achieved full control‑flow hijacks in 4% of the trials, while Claude Mythos Preview did so in 6%. Both models outperform earlier versions such as Claude Opus 4.6 and GLM‑5.2, which succeeded in none of the trials. This indicates that a significant threshold in adversarial exploitation capabilities has been crossed by the newer models.
Simon Willison
Aug 26
Qwen3.8-Flash-Next
Qwen3.8-Flash-Next is an open‑weights multimodal Mixture‑of‑Experts (MoE) model previewing the architecture of Qwen4. It contains 125 B tokens with only 6 B active, giving a performance boost. The author has tested it on a DGX Spark with Unsloth quantized models, exploring variants like UD‑IQ1_S and UD‑Q2_K_XL, and highlighted a high‑reasoning‑effort example from UD‑Q2_K_XL.
arXiv AI
4d ago
Mingbird: A Local-First Agent Harness Enabling Small Open Models to Complete Real Tasks
Mingbird is a local‑first agent harness designed for small open‑weight language models (2–9 B) that run on ordinary laptops. It introduces ten mechanisms—such as a byte‑level net‑zero prefill budget, a finish gate that re‑reads the task before accepting completion, and signature‑level loop detection—to address common failure modes that arise from the harness rather than the model itself. In controlled experiments on the LRAB benchmark and the $ au^2$‑bench, Mingbird achieves higher overall scores (0.886 and 0.856 respectively) compared to other harnesses, and its ablation studies show that each mechanism contributes measurable performance gains.
Hugging Face Trending Papers
Aug 6
CodeGrep: An RL-Trained Retrieval Agent for LLM Coding Agents
Modern LLM coding agents such as Claude Code and OpenHands share a common inefficiency: they spend much of their token budget finding the file to patch, rather than patching it. On SWE-Bench Verified, a 30B OpenHands agent averages 23 rounds and 631K tokens per resolved issue, with many calls spent on grep, glob, and view_file during repository exploration.
arXiv AI
Jun 11
CRANE: Constrained Reasoning Injection for Code Agents via Nullspace Editing
arXiv:2605. 14084v2 Announce Type: replace-cross Abstract: Code agents must both reason over long-horizon repository state and obey strict tool-use protocols.
Simon Willison
Sep 17
Bonsai 2 27B: Near-Lossless Compression in a 9x Smaller Footprint
My comment on Bonsai 2 27B: Near-Lossless Compression in a 9x Smaller Footprint — Hacker News.If you want to try out out the GGUFs from https://huggingface.co/prism-ml/Ternary-Bonsai-2-27B-gguf#...
Simon Willison
Aug 12
DeepSeek V4 Pro 0813 (on OpenRouter)
DeepSeek V4 Pro 0813 (on OpenRouter) The latest DeepSeek Pro model is now available, via API only. I had to link to OpenRouter because DeepSeek don't have any obvious announcement page for their new model.
Simon Willison
Sep 25
Quoting John Gruber
The article discusses Meta’s new AI system, Muse, which offers each user a persistent Linux VM in the cloud and is marketed as an easy-to-use, consumer‑friendly agentic AI. It highlights the system’s technical innovation and the company’s packaging as a cute mascot, while noting that users may not fully grasp the power and potential danger of such an advanced tool, especially when running it locally on a Mac.
arXiv AI
Aug 7
Recursive Synthesis for Long-Horizon Terminal Tasks
arXiv:2608. 05466v1 Announce Type: new Abstract: High-quality long-horizon training data for terminal agents is expensive to produce, often costing hundreds to thousands of dollars per task, because each task must keep the instruction, environment, reference solution, and verifier mutually consistent.