Simon Willison
3d ago
Mojo🔥 is now open source
Mojo🔥 is now open source The Mojo programming language has been promising an open source release since May 2023 . Last week they shipped their 1.
smolmachines / smolvm as a sandbox for untrusted Python & JavaScript
Research: smolmachines / smolvm as a sandbox for untrusted Python & JavaScript I tasked Claude Fable 5 running in Claude Code for web with the following research task: Put https://smolmachines. com through its paces as a fast secure sandbox.
Related stories
arXiv AI
Jun 3
Agent libOS: A Library-OS-Inspired Runtime for Long-Running, Capability-Controlled LLM Agents
arXiv:2606. 03895v1 Announce Type: cross Abstract: Large language model (LLM) agents are evolving from request-response assistants into long-running software actors: they maintain state across model calls, fork subtasks, wait for external events, request human authority, generate tools, and perform side effects that must be resumed and audited.
Hugging Face Trending Papers
Jun 2
Agent libOS: A Library-OS-Inspired Runtime for Long-Running, Capability-Controlled LLM Agents
Large language model (LLM) agents are evolving from request-response assistants into long-running software actors: they maintain state across model calls, fork subtasks, wait for external events, request human authority, generate tools, and perform side effects that must be resumed and audited. This paper presents Agent libOS, a library-OS-inspired runtime substrate for LLM agents.
Simon Willison
2d ago
Quoting Jeremy Morrell
My hypothesis is that there is a new opportunity for Extensible Software on the web . LLMs radically lower the cost of authoring extensions, and modern sandbox primitives lower the deployment cost and provide good security boundaries.
Simon Willison
1d ago
A shot-scraper-style JSON API on Bun 1.4's new Bun.WebView
Research: A shot-scraper-style JSON API on Bun 1. 4's new Bun.
arXiv AI
Jun 9
SecureVibeBench: Benchmarking Secure Vibe Coding of AI Agents via Reconstructing Vulnerability-Introducing Scenarios
arXiv:2509. 22097v5 Announce Type: replace-cross Abstract: Large language model-powered code agents are rapidly transforming software engineering, yet the security risks of their generated code have become a critical concern.
arXiv AI
Jul 1
Understanding and Evaluating Claw-like Agent Security Through a Computer-Systems Lens
arXiv:2606. 30755v1 Announce Type: cross Abstract: Claw-like AI agents (e.
Towards Data Science
Jun 5
My AI Couldn’t See My Files — I Built a Zero-Dependency MCP Server
I got tired of copying files into an AI chat just to get feedback. So I built a pure Python MCP server that gives AI tools direct access to my local project—no frameworks, no dependencies.
arXiv AI
Jul 14
Mako: A Self-Evolving Agentic Operating System (SE-AOS) for Autonomous Web Exploitation
arXiv:2607. 11288v1 Announce Type: cross Abstract: We introduce the Self-Evolving Agentic Operating System (SE-AOS): a new class of AI agent that treats exploit capability as a mutable, versioned kernel it extends at runtime, observing its own failures, synthesising new capabilities, proving them against a live target, and hot-loading them back into itself.
Simon Willison
Aug 11
Stealing Reasoning Traces from Proprietary LLM APIs
Stealing Reasoning Traces from Proprietary LLM APIs A vanity domain name ( stolen-thoughts. com ) for a neat paper : Anthropic, OpenAI, and Google return encrypted chain-of-thought blocks to clients that can be replayed across sessions, users, and models.
Simon Willison
Aug 10
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.
arXiv AI
Jun 2
Benchmarking Security Risk Detection and Verification in Open Agentic Skill Ecosystems
arXiv:2606. 00925v1 Announce Type: cross Abstract: Open agent platforms allow community contributors to publish reusable skills that agents can invoke at runtime.