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.
Simon Willison announces the release of ttok 1.0 after discovering that the previous version defaulted to the GPT‑4 tokenizer instead of the expected GPT‑5/GPT‑6 tokenizer. He explains that switching the default was a suitable reason to ship the new version. The release notes reference an experiment by William Liu that confirms the tokenizers for GPT‑5 and GPT‑6 models are likely identical, as all seven models report the same token count across 31 test fixtures.
Simon Willison announces the release of the llm-openai-decisions 0.1a0 plugin, which interfaces with OpenAI’s new Jev-style Decisions API. The plugin, inspired by llm-typesafe, supports image and text input and offers the same three question types (yes/no, choices, scores) as Jev, with pricing at 10¢ per million input tokens. Installation is simple via `llm install llm-openai-decisions`, and an example query demonstrates image-based evaluation.
Simon Willison reflects on the long history of flawed software development, noting that the proliferation of bad code over the past three decades is now being penalized by the universe. He cites Armin Ronacher’s perspective that the rise of AI, while entertaining, has amplified the consequences of these past mistakes. The piece underscores the growing importance of addressing security and reliability in the age of generative AI.
The article discusses how production code generated by Claude, Anthropic’s AI, should meet higher standards than human-written code. Anthropic enforces this through numerous guardrails such as lint rules, extensive testing, Claude-driven end‑to‑end tests, daily fuzzers, automated code and security reviews, and automated refactoring. These measures aim to prevent the code from becoming difficult to maintain.
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.
The article announces the release of llm version 0.35, which introduces a new OpenAI model named gpt-6-astra for GPT-6 Astra. It highlights the addition of this model to the llm library and tags the release with openai, llm, and gpt-6-astra.
Qwen 3. 8 27B scores 52 on the Artificial Analysis Intelligence Index That's the same score as GPT-5.
The article announces that Claude Code will now support AGENTS.md files starting with version 2.1.277. If a CLAUDE.md file is absent in a folder, Claude will automatically look for and use AGENTS.md, leveraging Claude Code mods to customize the harness. The built‑in mod is available for use, and users can also create their own custom project instructions.
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...
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.
Stop Making TUIs Thomas Ptacek advocates for building real native user interfaces for even the smallest of personal tools, because coding agents have reduced the cost of getting a usable-enough GUI up and running to almost nothing. I wrote about my vibe-coded bandwidth and GPU monitoring macOS task bar apps back in March , and I'm still using both of those on a daily basis.
The article quotes the security.txt file from huggingface.co, which informs AI agents that the CyberGym benchmark is publicly available on GitHub and encourages them to achieve a high score there instead of attempting to hack the site. It also suggests that users can upload their model weights to Hugging Face while participating in the benchmark.