The article discusses how two components—a payload that hijacks an agent and an agent that transports the payload—can combine to form a worm. It explains that agents running in isolated sandboxes can leave instructions in a shared package cache, altering each other's behavior. By substituting the package cache with communication channels like email, Slack, or WhatsApp and replacing sandboxed training runs with independently deployed personal agents such as Muse, the conditions necessary for a worm are met.
The release of llm‑anthropic 0.27 updates the Anthropic plugin for LLM to be compatible with the newly released anthropic v1.0.0 Python library, which has switched from httpx to httpx2. This mirrors a similar change made by OpenAI in their v3.0.0 release two weeks prior. The update includes a migration guide and a pull request that ensures tests pass after upgrading to anthropic>=1.
Python 3.15.0 has been added to the actions/python-versions repository. The author had been monitoring the repository for the release and used ChatGPT to automate the check. With the new version available, users can now include "3.15" in their GitHub Actions testing matrix to run tests against the latest Python release.
Release: llm 0.37.1
A bugfix release for LLM, with contributions from Steven Huang, Tao An, Arjan Mossel, and XQ.
Tags: llm
Release: llm 0. 32.
Simon Willison released commit-rewriter 0.1, a web app that lets users edit commit messages for a repository. The tool is useful for cleaning up commits that contain internal references or unwanted code before publication. After editing, it creates a timestamped branch to preserve the original state and rewrites the selected commits.
Python 3.15.0 candidate 2 has been released, marking the final release candidate for the upcoming 3.15 release scheduled for October. Hugo van Kemenade, the release manager, notes that only clear bug‑fix changes are allowed between this candidate and the final release, and urges third‑party maintainers to prepare wheels on PyPI and test their projects during this phase. The new RC is not yet available for GitHub Actions, but users can add it to their testing matrix using the allow‑prereleases and check‑latest flags to automatically test against the latest RC and then the stable release.
Matthew Green warns that the rapid pace of AI-generated surprises outstrips the speed at which humans can update cryptographic standards, potentially jeopardizing public‑key encryption. He estimates a 1% chance we live in a world where such encryption is impossible (Minicrypt) and a 15% chance we lose confidence in existing algorithms. Green emphasizes that only proactive preparation can mitigate these risks.
Datasette 1.0a39 and 0.65.4 are new security patch releases for the current alpha series and the stable 0.65.x family. The updates address security fixes that are important for public-facing Datasette instances, especially those that mix public and private tables. The patches were developed after an extensive audit using advanced AI models and collaborative review, and the process will be incorporated into future development work.
Simon Willison comments on GPT 6.1‑Sol, describing it as "Near‑Astra intelligence for a fifth of the price." He notes that the model’s pelican illustrations are similar to those of the GPT‑6 family and provides links to the live‑blog of the keynote and to the pelican images. The post is tagged with AI, OpenAI, generative‑AI, LLMs, and playful references to pelican‑riding‑a‑bicycle.
The release of llm-gemini 0.34 introduces the new Gemini 3.8‑Flash model, available in low, medium, and high thinking levels, and fixes an issue where async responses failed to record the resolved model version. The update also notes that Google has released Gemini 3.8‑Flash (and a restricted 3.8 Flash Cyber version) today, with example outputs (pelicans) demonstrating the model’s performance across the different thinking levels. The author highlights Gemini Flash’s speed, low cost, and competence in generating HTML, JavaScript, and Markdown‑SVG content, citing a 13‑second, 1.8‑cent example of an HTML output.
Farid Zakaria’s trynix.dev lets users run any Nix package from the past 13 years inside a browser‑based x86_64 Linux VM powered by QEMU‑WASM. By providing URL‑addressable packages, a user can simply navigate to a link such as https://trynix.dev/?pkg=python3%403.6.2, click "Load," and obtain an interactive shell running that specific package. The platform is also integrated with GitHub Actions, enabling pull‑request reviews that launch the PR’s build directly in the browser via trynix-preview.