smolmachines / smolvm as a sandbox for untrusted Python & JavaScript
Testing smolvm 1.8.3 as a sandbox for untrusted Python & JavaScript, using hardware-isolated VMs with resource limits and no network.
Simon Willison — Independent developer and writer documenting practical experiments, tools, and deep analysis around large language models, generative AI, web development, security, and emerging programming workflows through detailed posts and daily TILs.
381 articles from this blog
Testing smolvm 1.8.3 as a sandbox for untrusted Python & JavaScript, using hardware-isolated VMs with resource limits and no network.
A quote from Jeremy Morrell about extensible software on the web, highlighting LLMs lowering extension authoring costs and sandbox primitives for secure deployment.
Simon Willison discusses how AI coding agents change productivity metrics and the importance of conceptual integrity in software development.
Mojo programming language is now open source under Apache 2, with compiler and toolchain released, aiming for painless GPU programming with Python-inspired syntax.
Qwen 3.8 27B scores 52 on Artificial Analysis Intelligence Index, matching GPT-5.6 Luna and near larger models.
17th August 2026 - Link Blog We Tracked a Shipment of Rare Books. It Ended at an Amazon AI Training Facility. Excellent piece of reporting from 404 Me
16th August 2026 I started building my markdown-svg-renderer tool in May, but I've since added enough features to it that it's worth talking about her
Qwen 3.8 27B is excellent, but it defaults to wildly overthinking things 16th August 2026 Friday’s big release was Qwen 3.8 27B, an Apache 2 licensed
Dario Amodei discusses public distrust of AI, arguing it stems from unfulfilled promises rather than risk warnings, and advocates for tangible benefits over marketing.
A browser-based tool for chatting with any OpenAI Responses-compatible API endpoint, supporting custom headers, local conversation storage, and multiple sessions.
A blog post about using LLM hallucination for tagging blog content, then mapping imagined tags to existing vocabulary via vector embeddings.
sqlite-utils 4.2.1 fixes a crashing bug caused by missing typing-extensions dependency and adds a smoke test for CLI without dev dependencies.
sqlite-utils 4.2 release: Python CLI/library for SQLite, enhancing table.transform() with better schema preservation and new introspection features.
llm-gemini 0.33 plugin adds support for Gemini 3.7 Flash and other models, with LLM 0.32 compatibility for reasoning traces and server-side tools.
Release of alchemy-utils 0.1a1, a cross-database sqlite-utils built on SQLAlchemy, with performance boosts for DuckDB exports and CSV imports.
DeepSeek V4 Pro 0813 is now available via API on OpenRouter, with no official announcement page yet. Open weights likely, benchmarks shared via community.
Release of alchemy-utils 0.1a0, a cross-database sqlite-utils built on SQLAlchemy, supporting PostgreSQL, SQLite, and DuckDB.
A quote about AI's impact on software engineering, highlighting how AI tools can lead to convoluted projects that no one fully understands.
A blog post discussing AI writing tools, emphasizing that no lossless transformations of text exist and engineers must own their words.
A security paper reveals how encrypted reasoning traces from proprietary LLM APIs can be replayed and jailbroken to recover hidden chain-of-thought, now fixed.