Simon Willison
Sep 28
llm-anthropic 0.30
Release: llm-anthropic 0.30 In addition to Claude Sonnet 5.5, this release adds the ability to run llm anthropic refresh to refresh the list of Anthropic models directly from their API - which...
llm-echo 0.5
The article announces the release of llm-echo version 0.5, a debug plugin that simulates an LLM by echoing back prompts without actual model inference. The new version updates token usage calculations to include tool calls, system prompts, and reasoning tokens. An example shows how to invoke the plugin and view the resulting prompt and token usage.
Related stories
Simon Willison
Sep 2
llm 0.34
The release of llm 0.34 introduces a new feature that enhances log output by including response duration in both milliseconds and a human‑readable format. The short log view now contains a dedicated duration_ms field. Additionally, the update incorporates multiple bug fixes and a notable performance boost to llm logs, attributed to waveplate integration.
Simon Willison
Sep 22
llm 0.36
The release of llm 0.36 introduces new OpenAI models gpt-6-sol and gpt-6-luna, and adds support for model plugins to declare that they do not support conversations via supports_conversation = False. When such models receive assistant or tool history, llm raises a ConversationNotSupported error and the chat interface rejects them before starting a session. Additional changes include wrapping reasoning traces in Markdown output with <details> tags and bug fixes from five contributors.
Simon Willison
6d ago
llm-tools-datasette 0.1.1
The article announces the release of llm-tools-datasette version 0.1.1. It explains that updating LLM to use httpx2 caused compatibility issues with plugins that relied on httpx, including llm-tools-datasette, which has now been fixed. The release notes highlight the resolution of this plugin breakage.
Towards Data Science
Jun 18
Structured Outputs with LLMs: JSON Mode, Function Calling, and When to Use Each
Getting reliable, readable responses out of your LLM, and knowing which tool to reach for The post Structured Outputs with LLMs: JSON Mode, Function Calling, and When to Use Each appeared first on Towards Data Science .
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.
Simon Willison
Aug 24
llm-anthropic 0.27
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.
Simon Willison
Oct 8
ttok 0.4
ttok 0.4 is a command‑line tool for counting tokens using OpenAI’s tiktoken library. The release fixes a Click warning, updates continuous integration, and adds a new --list-models command to display available models. It can be used with uvx to count tokens from any input, such as piping a file into the tool.
Towards Data Science
Aug 9
How to Implement Structured Output with Local LLMs
Why use it? How to implement it?
arXiv AI
Oct 16
LLMON: An LLM-native Markup Language to Leverage Structure and Semantics at the LLM Interface
The paper introduces LLMON, an LLM-native markup language designed to encode the structure and semantic metadata of textual inputs for large language models. By distinguishing components such as instructions and data within prompts, LLMON aims to reduce model confusion and mitigate security risks like prompt injection. The authors outline design requirements, present the language, and provide preliminary evidence that incorporating LLMON can improve model accuracy, safety, and security during training and inference.
Simon Willison
Aug 22
Quoting Linus Torvalds
The article recounts a challenging debug session that was significantly aided by an AI assistant. Despite the AI initially claiming the problem was unsolvable and suggesting a report be written instead, it persisted, adding debug code and analyzing it as the author pushed forward. Ultimately, the author credits the AI with writing the commit message for the fix.
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.