llm-willison
![Brian Piercy](data:image/svg+xml;utf8,<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24" fill="%230A66C2"><path d="M20.447 20.452H16.89v-5.569c0-1.328-.027-3.037-1.852-3.037-1.853 0-2.136 1.445-2.136 2.939v5.667H9.351V9h3.414v1.561h.046c.477-.9 1.637-1.85 3.37-1.85 3.601 0 4.267 2.37 4.267 5.455v6.286zM5.337 7.433a1.982 1.982 0 1 1 0-3.964 1.982 1.982 0 0 1 0 3.964zm1.782 13.019H3.555V9h3.564v11.452zM22.225 0H1.771C.792 0 0 .774 0 1.729v20.542C0 23.227.792 24 1.771 24h20.451C23.2 24 24 23.227 24 22.271V1.729C24 .774 23.2 0 22.222 0h.003z"/></svg>)
Access large language models from the command-line
Here's the handout I prepared for my NICAR 2026 workshop "Coding agents for data analysis" - a three hour session aimed at data journalists demonstrating ways that tools like Claude …
This is the third in my annual series reviewing everything that happened in the LLM space over the past 12 months. For previous years see Stuff we figured out about …
OpenAI half-relased this model earlier this month, adding it to their Codex CLI tool but not their API. Today they've fixed that - the new model can now be accessed …
Christopher Smith ran a mini hackathon in Albany New York at the weekend around uses of my LLM - the first in-person event I'm aware of dedicated to that project! …
I presented a three hour workshop at PyCon US yesterday titled Building software on top of Large Language Models. The goal of the workshop was to give participants everything they …
First there was Claude Code in February, then OpenAI Codex (CLI) in April, and now Gemini CLI in June. All three of the largest AI labs now have their own …
I [added tool-support](https://github.com/simonw/llm-mistral/issues/31) to my plugin for accessing the Mistral API from LLM today, plus support for Mistral's new [Codestral Embed](https://simonwillison.net/2025/May/28/codestral-embed/) embedding model. An interesting challenge here is that I'm …
When I [shipped LLM 0.26](https://simonwillison.net/2025/May/27/llm-tools/) yesterday one of the things I was most excited about was seeing what new tool plugins people would build for it. Dan Turkel's [llm-tools-exa](https://github.com/daturkel/llm-tools-exa) is …
Anthony Shaw's [llm-github-models](https://github.com/tonybaloney/llm-github-models) plugin just got an upgrade: it now supports [LLM 0.26 tool use](https://simonwillison.net/2025/May/27/llm-tools/) for a subset of the models hosted on the [GitHub Models API](https://docs.github.com/en/github-models), contributed by [Caleb …
Here's a quick demo of the kind of casual things I use LLMs for on a daily basis. I just found out that Perplexity offer their Deep Research feature via …
LLM 0.26 is out with the biggest new feature since I started the project: support for tools. You can now use the LLM CLI tool—and Python library—to grant LLMs from …
Anthropic publish most of the system prompts for their chat models as part of their release notes. They recently shared the new prompts for both Claude Opus 4 and Claude …
Direct link to a PDF on Anthropic's CDN because they don't appear to have a landing page anywhere for this document. Anthropic's system cards are always worth a look, and …
Really neat CLI tool for bulk renaming of files and directories by Ayooluwa Isaiah, written in Go and designed to work cross-platform. There's a _lot_ of great design in this. …
New release of my LLM plugin for Anthropic adding the new Claude 4 Opus and Sonnet models. You can see pelicans on bicycles generated using the new plugin at the …
Inspired by my previous [llm-video-frames](https://github.com/simonw/llm-video-frames) plugin, I thought it would be neat to have a plugin for LLM that can take a PDF and turn that into an image-per-page so …
This is an extremely useful, detailed set of explanations by [@AlpinDale](https://x.com/AlpinDale) covering the various different sampling strategies used by modern LLMs. LLMs return a set of next-token probabilities for every …
Doug Turnbull recently wrote about how [all search is structured now](https://softwaredoug.com/blog/2025/04/02/all-search-structured-now): Many times, even a small open source LLM will be able to turn a search query into reasonable …
In a follow-up to the research that brought us the [delightful Golden Gate Claude](https://simonwillison.net/2024/May/24/golden-gate-claude/) last year, Anthropic have published two new papers about LLM interpretability: - [Circuit Tracing: Revealing Computational …
Google's Gemma 3 model (the 27B variant is particularly capable, I've been trying it out [via Ollama](https://ollama.com/library/gemma3)) supports function calling exclusively through prompt engineering. The official documentation describes two recommended …
There’s a new release from Google Gemini this morning: the first in the Gemini 2.5 series. Google call it “a thinking model, designed to tackle increasingly complex problems”. It’s already …
Spectacular new open geospatial project by [Dan Snow](https://sno.ws/): > OpenTimes is a database of pre-computed, point-to-point travel times between United States Census geographies. It lets you download bulk travel time …
Mistral Small 3 [came out in January](https://simonwillison.net/2025/Jan/30/mistral-small-3/) and was a notable, genuinely excellent local model that used an Apache 2.0 license. Mistral Small 3.1 offers a significant improvement: it's multi-modal …
Here's the handout for a workshop I presented this morning at [NICAR 2025](https://www.ire.org/training/conferences/nicar-2025/) on web scraping, focusing on lesser know tips and tricks that became possible only with recent developments …
New closed-source specialist OCR model by Mistral - you can feed it images or a PDF and it produces Markdown with optional embedded images. It's available [via their API](https://docs.mistral.ai/api/#tag/ocr), or …
I added [schema support](https://simonwillison.net/2025/Feb/28/llm-schemas/) to this plugin which adds support for the [Mistral API](https://docs.mistral.ai/api/) to LLM. Release notes: - Support for LLM [schemas](https://llm.datasette.io/en/stable/schemas.html). [#19](https://github.com/simonw/llm-mistral/issues/19) - `-o prefix '{'` …
This release of the `llm-ollama` plugin adds support for [schemas](https://simonwillison.net/2025/Feb/28/llm-schemas/), thanks to a [PR by Adam Compton](https://github.com/taketwo/llm-ollama/pull/36). Ollama provides very robust support for this pattern thanks to their [structured outputs](https://ollama.com/blog/structured-outputs) …
Neat open source project on the GitHub organisation for the UK government's Department for Business and Trade: a "Python virtual filesystem for SQLite to read from and write to S3." …
I just released llm-smollm2, a new plugin for LLM that bundles a quantized copy of the SmolLM2-135M-Instruct LLM inside of the Python package. This means you can now pip install …
I started running a basic link blog on this domain back in November 2003—publishing links (which I called “blogmarks”) with a title, URL, short snippet of commentary and a “via” …
o3-mini is out today. As with other o-series models it’s a slightly difficult one to evaluate—we now need to decide if a prompt is best run using GPT-4o, o1, o3-mini …
Johann Rehberger snagged a copy of the [ChatGPT Operator](https://simonwillison.net/2025/Jan/23/introducing-operator/) system prompt. As usual, the system prompt doubles as better written documentation than any of the official sources. It asks users …
New release of my [LLM](https://llm.datasette.io/) CLI tool and Python library. A bunch of accumulated fixes and features since the start of December, most notably: - Support for OpenAI's [o1 model](https://platform.openai.com/docs/models#o1) …
DeepSeek are the Chinese AI lab who dropped the best currently available open weights LLM on Christmas day, DeepSeek v3. That model was trained in part using their unreleased R1 …
New paper from Microsoft describing their top eight lessons learned red teaming (deliberately seeking security vulnerabilities in) 100 different generative AI models and products over the past few years. …
A lot has happened in the world of Large Language Models over the course of 2024. Here’s a review of things we figured out about the field in the past …
Last week Google introduced Gemini Pro 1.5, an enormous upgrade to their Gemini series of AI models. Gemini Pro 1.5 has a 1,000,000 token context size. This is huge—previously that …
Seth Michael Larson pointed out that the Python gzip module can be used as a CLI tool like this:
Large language models such as GPT-3/4, LLaMA and PaLM work in terms of tokens. They take text, convert it into tokens (integers), then predict which tokens should come next. Playing …
I figured out how to run a SQL query directly against a CSV file using the sqlite3 command-line utility:
I’m going to describe a way to put together a world-class continuous deployment infrastructure for your side-project without spending any money. With continuous deployment every code commit is tested against …