Simon Willison’s Weblog

llm-fragments-go (via) Filippo Valsorda released the first plugin by someone other than me that uses LLM's new register_fragment_loaders() plugin hook I announced the other day.

Install with llm install llm-fragments-go and then:

You can feed the docs of a Go package into LLM using the go: fragment with the package name, optionally followed by a version suffix.

llm -f go:golang.org/x/mod/sumdb/note@v0.23.0 "Write a single file command that generates a key, prints the verifier key, signs an example message, and prints the signed note."

The implementation is just 33 lines of Python and works by running these commands in a temporary directory:

go mod init llm_fragments_go
go get golang.org/x/mod/sumdb/note@v0.23.0
go doc -all golang.org/x/mod/sumdb/note

# 3:19 pm / generative-ai, llm, plugins, go, ai, llms, filippo-valsorda

Django: what’s new in 5.2. Adam Johnson provides extremely detailed unofficial annotated release notes for the latest Django.

I found his explanation and example of Form BoundField customization particularly useful - here's the new pattern for customizing the class= attribute on the label associated with a CharField:

from django import forms

class WideLabelBoundField(forms.BoundField):
    def label_tag(self, contents=None, attrs=None, label_suffix=None):
        if attrs is None:
            attrs = {}
        attrs["class"] = "wide"
        return super().label_tag(contents, attrs, label_suffix)

class NebulaForm(forms.Form):
    name = forms.CharField(
        max_length=100,
        label="Nebula Name",
        bound_field_class=WideLabelBoundField,
    )

I'd also missed the new HttpResponse.get_preferred_type() method for implementing HTTP content negotiation:

content_type = request.get_preferred_type(
    ["text/html", "application/json"]
)

# 4:27 pm / adam-johnson, django, python

llm-docsmith (via) Matheus Pedroni released this neat plugin for LLM for adding docstrings to existing Python code. You can run it like this:

llm install llm-docsmith
llm docsmith ./scripts/main.py -o

The -o option previews the changes that will be made - without -o it edits the files directly.

It also accepts a -m claude-3.7-sonnet parameter for using an alternative model from the default (GPT-4o mini).

The implementation uses the Python libcst "Concrete Syntax Tree" package to manipulate the code, which means there's no chance of it making edits to anything other than the docstrings.

Here's the full system prompt it uses.

One neat trick is at the end of the system prompt it says:

You will receive a JSON template. Fill the slots marked with <SLOT> with the appropriate description. Return as JSON.

That template is actually provided JSON generated using these Pydantic classes:

class Argument(BaseModel):
    name: str
    description: str
    annotation: str | None = None
    default: str | None = None

class Return(BaseModel):
    description: str
    annotation: str | None

class Docstring(BaseModel):
    node_type: Literal["class", "function"]
    name: str
    docstring: str
    args: list[Argument] | None = None
    ret: Return | None = None

class Documentation(BaseModel):
    entries: list[Docstring]

The code adds <SLOT> notes to that in various places, so the template included in the prompt ends up looking like this:

{
  "entries": [
    {
      "node_type": "function",
      "name": "create_docstring_node",
      "docstring": "<SLOT>",
      "args": [
        {
          "name": "docstring_text",
          "description": "<SLOT>",
          "annotation": "str",
          "default": null
        },
        {
          "name": "indent",
          "description": "<SLOT>",
          "annotation": "str",
          "default": null
        }
      ],
      "ret": {
        "description": "<SLOT>",
        "annotation": "cst.BaseStatement"
      }
    }
  ]
}

# 6:09 pm / prompt-engineering, llm, python, plugins, generative-ai, ai, pydantic

LLM pricing calculator (updated). I updated my LLM pricing calculator this morning (Claude transcript) to show the prices of various hosted models in a sorted table, defaulting to lowest price first.

Amazon Nova and Google Gemini continue to dominate the lower end of the table. The most expensive models currently are still OpenAI's o1-Pro ($150/$600 and GPT-4.5 ($75/$150).

# 7:56 pm / claude, llm-pricing, ai, llms, vibe-coding, ai-assisted-programming, generative-ai, tools

Default styles for h1 elements are changing (via) Wow, this is a rare occurrence! Firefox are rolling out a change to the default user-agent stylesheet for nested <h1> elements, currently ramping from 5% to 50% of users and with full roll-out planned for Firefox 140 in June 2025. Chrome is showing deprecation warnings and Safari are expected to follow suit in the future.

What's changing? The default sizes of <h1> elements that are nested inside <article>, <aside>, <nav> and <section>.

These are the default styles being removed:

/* where x is :is(article, aside, nav, section) */
x h1 { margin-block: 0.83em; font-size: 1.50em; }
x x h1 { margin-block: 1.00em; font-size: 1.17em; }
x x x h1 { margin-block: 1.33em; font-size: 1.00em; }
x x x x h1 { margin-block: 1.67em; font-size: 0.83em; }
x x x x x h1 { margin-block: 2.33em; font-size: 0.67em; }

The short version is that, many years ago, the HTML spec introduced the idea that an <h1> within a nested section should have the same meaning (and hence visual styling) as an <h2>. This never really took off and wasn't reflected by the accessibility tree, and was removed from the HTML spec in 2022. The browsers are now trying to cleanup the legacy default styles.

This advice from that post sounds sensible to me:

• Do not rely on default browser styles for conveying a heading hierarchy. Explicitly define your document hierarchy using <h2> for second-level headings, <h3> for third-level, etc.
• Always define your own font-size and margin for <h1> elements.

# 3:54 am / css, html, firefox, mozilla, browsers, safari, chrome, web-standards

llm-fragments-rust (via) Inspired by Filippo Valsorda's llm-fragments-go, Francois Garillot created llm-fragments-rust, an LLM fragments plugin that lets you pull documentation for any Rust crate directly into a prompt to LLM.

I really like this example, which uses two fragments to load documentation for two crates at once:

llm -f rust:rand@0.8.5 -f rust:tokio "How do I generate random numbers asynchronously?"

The code uses some neat tricks: it creates a new Rust project in a temporary directory (similar to how llm-fragments-go works), adds the crates and uses cargo doc --no-deps --document-private-items to generate documentation. Then it runs cargo tree --edges features to add dependency information, and cargo metadata --format-version=1 to include additional metadata about the crate.

# 5:36 pm / llm, rust, ai-assisted-programming, plugins, generative-ai, ai, llms

Stevens: a hackable AI assistant using a single SQLite table and a handful of cron jobs. Geoffrey Litt reports on Stevens, a shared digital assistant he put together for his family using SQLite and scheduled tasks running on Val Town.

The design is refreshingly simple considering how much it can do. Everything works around a single memories table. A memory has text, tags, creation metadata and an optional date for things like calendar entries and weather reports.

Everything else is handled by scheduled jobs to popular weather information and events from Google Calendar, a Telegram integration offering a chat UI and a neat system where USPS postal email delivery notifications are run through Val's own email handling mechanism to trigger a Claude prompt to add those as memories too.

Here's the full code on Val Town, including the daily briefing prompt that incorporates most of the personality of the bot.

# 8:58 pm / geoffrey-litt, sqlite, generative-ai, val-town, ai, llms

Using LLMs as the first line of support in Open Source (via) From reading the title I was nervous that this might involve automating the initial response to a user support query in an issue tracker with an LLM, but Carlton Gibson has better taste than that.

The open contribution model engendered by GitHub — where anonymous (to the project) users can create issues, and comments, which are almost always extractive support requests — results in an effective denial-of-service attack against maintainers. [...]

For anonymous users, who really just want help almost all the time, the pattern I’m settling on is to facilitate them getting their answer from their LLM of choice. [...] we can generate a file that we offer users to download, then we tell the user to pass this to (say) Claude with a simple prompt for their question.

This resonates with the concept proposed by llms.txt - making LLM-friendly context files available for different projects.

My simonw/docs-for-llms contains my own early experiment with this: I'm running a build script to create LLM-friendly concatenated documentation for several of my projects, and my llm-docs plugin (described here) can then be used to ask questions of that documentation.

It's possible to pre-populate the Claude UI with a prompt by linking to https://claude.ai/new?q={PLACE_HOLDER}, but it looks like there's quite a short length limit on how much text can be passed that way. It would be neat if you could pass a URL to a larger document instead.

ChatGPT also supports https://chatgpt.com/?q=your-prompt-here (again with a short length limit) and directly executes the prompt rather than waiting for you to edit it first(!)

# 4:54 am / open-source, llms, ai, generative-ai, carlton-gibson, chatgpt, claude

SQLite File Format Viewer (via) Neat browser-based visual interface for exploring the structure of a SQLite database file, built by Visal In using React and a custom parser implemented in TypeScript.

# 2:35 pm / typescript, react, sqlite

openai/codex. Just released by OpenAI, a "lightweight coding agent that runs in your terminal". Looks like their version of Claude Code, though unlike Claude Code Codex is released under an open source (Apache 2) license.

Here's the main prompt that runs in a loop, which starts like this:

You are operating as and within the Codex CLI, a terminal-based agentic coding assistant built by OpenAI. It wraps OpenAI models to enable natural language interaction with a local codebase. You are expected to be precise, safe, and helpful.

You can:
- Receive user prompts, project context, and files.
- Stream responses and emit function calls (e.g., shell commands, code edits).
- Apply patches, run commands, and manage user approvals based on policy.
- Work inside a sandboxed, git-backed workspace with rollback support.
- Log telemetry so sessions can be replayed or inspected later.
- More details on your functionality are available at codex --help

The Codex CLI is open-sourced. Don't confuse yourself with the old Codex language model built by OpenAI many moons ago (this is understandably top of mind for you!). Within this context, Codex refers to the open-source agentic coding interface. [...]

I like that the prompt describes OpenAI's previous Codex language model as being from "many moons ago". Prompt engineering is so weird.

Since the prompt says that it works "inside a sandboxed, git-backed workspace" I went looking for the sandbox. On macOS it uses the little-known sandbox-exec process, part of the OS but grossly under-documented. The best information I've found about it is this article from 2020, which notes that man sandbox-exec lists it as deprecated. I didn't spot evidence in the Codex code of sandboxes for other platforms.

# 5:25 pm / ai-assisted-programming, generative-ai, ai-agents, openai, ai, llms, open-source, prompt-engineering, sandboxing, macos

Introducing OpenAI o3 and o4-mini. OpenAI are really emphasizing tool use with these:

For the first time, our reasoning models can agentically use and combine every tool within ChatGPT—this includes searching the web, analyzing uploaded files and other data with Python, reasoning deeply about visual inputs, and even generating images. Critically, these models are trained to reason about when and how to use tools to produce detailed and thoughtful answers in the right output formats, typically in under a minute, to solve more complex problems.

I released llm-openai-plugin 0.3 adding support for the two new models:

llm install -U llm-openai-plugin
llm -m openai/o3 "say hi in five languages"
llm -m openai/o4-mini "say hi in five languages"

Here are the pelicans riding bicycles (prompt: Generate an SVG of a pelican riding a bicycle).

o3:

o4-mini:

Here are the full OpenAI model listings: o3 is $10/million input and $40/million for output, with a 75% discount on cached input tokens, 200,000 token context window, 100,000 max output tokens and a May 31st 2024 training cut-off (same as the GPT-4.1 models). It's a bit cheaper than o1 ($15/$60) and a lot cheaper than o1-pro ($150/$600).

o4-mini is priced the same as o3-mini: $1.10/million for input and $4.40/million for output, also with a 75% input caching discount. The size limits and training cut-off are the same as o3.

You can compare these prices with other models using the table on my updated LLM pricing calculator.

A new capability released today is that the OpenAI API can now optionally return reasoning summary text. I've been exploring that in this issue. I believe you have to verify your organization (which may involve a photo ID) in order to use this option - once you have access the easiest way to see the new tokens is using curl like this:

curl https://api.openai.com/v1/responses \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $(llm keys get openai)" \
  -d '{
    "model": "o3",
    "input": "why is the sky blue?",
    "reasoning": {"summary": "auto"},
    "stream": true
  }'

This produces a stream of events that includes this new event type:

event: response.reasoning_summary_text.delta
data: {"type": "response.reasoning_summary_text.delta","item_id": "rs_68004320496081918e1e75ddb550d56e0e9a94ce520f0206","output_index": 0,"summary_index": 0,"delta": "**Expl"}

Omit the "stream": true and the response is easier to read and contains this:

{
  "output": [
    {
      "id": "rs_68004edd2150819183789a867a9de671069bc0c439268c95",
      "type": "reasoning",
      "summary": [
        {
          "type": "summary_text",
          "text": "**Explaining the blue sky**\n\nThe user asks a classic question about why the sky is blue. I'll talk about Rayleigh scattering, where shorter wavelengths of light scatter more than longer ones. This explains how we see blue light spread across the sky! I wonder if the user wants a more scientific or simpler everyday explanation. I'll aim for a straightforward response while keeping it engaging and informative. So, let's break it down!"
        }
      ]
    },
    {
      "id": "msg_68004edf9f5c819188a71a2c40fb9265069bc0c439268c95",
      "type": "message",
      "status": "completed",
      "content": [
        {
          "type": "output_text",
          "annotations": [],
          "text": "The short answer ..."
        }
      ]
    }
  ]
}

# 5:46 pm / llm, openai, llm-tool-use, llm-pricing, ai, llms, llm-release, generative-ai, llm-reasoning

Start building with Gemini 2.5 Flash (via) Google Gemini's latest model is Gemini 2.5 Flash, available in (paid) preview as gemini-2.5-flash-preview-04-17.

Building upon the popular foundation of 2.0 Flash, this new version delivers a major upgrade in reasoning capabilities, while still prioritizing speed and cost. Gemini 2.5 Flash is our first fully hybrid reasoning model, giving developers the ability to turn thinking on or off. The model also allows developers to set thinking budgets to find the right tradeoff between quality, cost, and latency.

Gemini AI Studio product lead Logan Kilpatrick says:

This is an early version of 2.5 Flash, but it already shows huge gains over 2.0 Flash.

You can fully turn off thinking if needed and use this model as a drop in replacement for 2.0 Flash.

I added support to the new model in llm-gemini 0.18. Here's how to try it out:

llm install -U llm-gemini
llm -m gemini-2.5-flash-preview-04-17 'Generate an SVG of a pelican riding a bicycle'

Here's that first pelican, using the default setting where Gemini Flash 2.5 makes its own decision in terms of how much "thinking" effort to apply:

Here's the transcript. This one used 11 input tokens and 4266 output tokens of which 2702 were "thinking" tokens.

I asked the model to "describe" that image and it could tell it was meant to be a pelican:

A simple illustration on a white background shows a stylized pelican riding a bicycle. The pelican is predominantly grey with a black eye and a prominent pink beak pouch. It is positioned on a black line-drawn bicycle with two wheels, a frame, handlebars, and pedals.

The way the model is priced is a little complicated. If you have thinking enabled, you get charged $0.15/million tokens for input and $3.50/million for output. With thinking disabled those output tokens drop to $0.60/million. I've added these to my pricing calculator.

For comparison, Gemini 2.0 Flash is $0.10/million input and $0.40/million for output.

So my first prompt - 11 input and 4266 output(with thinking enabled), cost 1.4933 cents.

Let's try 2.5 Flash again with thinking disabled:

llm -m gemini-2.5-flash-preview-04-17 'Generate an SVG of a pelican riding a bicycle' -o thinking_budget 0

11 input, 1705 output. That's 0.1025 cents. Transcript here - it still shows 25 thinking tokens even though I set the thinking budget to 0 - Logan confirms that this will still be billed at the lower rate:

In some rare cases, the model still thinks a little even with thinking budget = 0, we are hoping to fix this before we make this model stable and you won't be billed for thinking. The thinking budget = 0 is what triggers the billing switch.

Here's Gemini 2.5 Flash's self-description of that image:

A minimalist illustration shows a bright yellow bird riding a bicycle. The bird has a simple round body, small wings, a black eye, and an open orange beak. It sits atop a simple black bicycle frame with two large circular black wheels. The bicycle also has black handlebars and black and yellow pedals. The scene is set against a solid light blue background with a thick green stripe along the bottom, suggesting grass or ground.

And finally, let's ramp the thinking budget up to the maximum:

llm -m gemini-2.5-flash-preview-04-17 'Generate an SVG of a pelican riding a bicycle' -o thinking_budget 24576

I think it over-thought this one. Transcript - 5174 output tokens of which 3023 were thinking. A hefty 1.8111 cents!

A simple, cartoon-style drawing shows a bird-like figure riding a bicycle. The figure has a round gray head with a black eye and a large, flat orange beak with a yellow stripe on top. Its body is represented by a curved light gray shape extending from the head to a smaller gray shape representing the torso or rear. It has simple orange stick legs with round feet or connections at the pedals. The figure is bent forward over the handlebars in a cycling position. The bicycle is drawn with thick black outlines and has two large wheels, a frame, and pedals connected to the orange legs. The background is plain white, with a dark gray line at the bottom representing the ground.

One thing I really appreciate about Gemini 2.5 Flash's approach to SVGs is that it shows very good taste in CSS, comments and general SVG class structure. Here's a truncated extract - I run a lot of these SVG tests against different models and this one has a coding style that I particularly enjoy. (Gemini 2.5 Pro does this too).

<svg width="800" height="500" viewBox="0 0 800 500" xmlns="http://www.w3.org/2000/svg">
  <style>
    .bike-frame { fill: none; stroke: #333; stroke-width: 8; stroke-linecap: round; stroke-linejoin: round; }
    .wheel-rim { fill: none; stroke: #333; stroke-width: 8; }
    .wheel-hub { fill: #333; }
    /* ... */
    .pelican-body { fill: #d3d3d3; stroke: black; stroke-width: 3; }
    .pelican-head { fill: #d3d3d3; stroke: black; stroke-width: 3; }
    /* ... */
  </style>
  <!-- Ground Line -->
  <line x1="0" y1="480" x2="800" y2="480" stroke="#555" stroke-width="5"/>
  <!-- Bicycle -->
  <g id="bicycle">
    <!-- Wheels -->
    <circle class="wheel-rim" cx="250" cy="400" r="70"/>
    <circle class="wheel-hub" cx="250" cy="400" r="10"/>
    <circle class="wheel-rim" cx="550" cy="400" r="70"/>
    <circle class="wheel-hub" cx="550" cy="400" r="10"/>
    <!-- ... -->
  </g>
  <!-- Pelican -->
  <g id="pelican">
    <!-- Body -->
    <path class="pelican-body" d="M 440 330 C 480 280 520 280 500 350 C 480 380 420 380 440 330 Z"/>
    <!-- Neck -->
    <path class="pelican-neck" d="M 460 320 Q 380 200 300 270"/>
    <!-- Head -->
    <circle class="pelican-head" cx="300" cy="270" r="35"/>
    <!-- ... -->

The LM Arena leaderboard now has Gemini 2.5 Flash in joint second place, just behind Gemini 2.5 Pro and tied with ChatGPT-4o-latest, Grok-3 and GPT-4.5 Preview.

# 8:56 pm / llm-release, gemini, llm, google, llm-reasoning, llm-pricing, llms, pelican-riding-a-bicycle, svg, logan-kilpatrick, lm-arena

MCP Run Python (via) Pydantic AI's MCP server for running LLM-generated Python code in a sandbox. They ended up using a trick I explored two years ago: using a Deno process to run Pyodide in a WebAssembly sandbox.

Here's a bit of a wild trick: since Deno loads code on-demand from JSR, and uv run can install Python dependencies on demand via the --with option... here's a one-liner you can paste into a macOS shell (provided you have Deno and uv installed already) which will run the example from their README - calculating the number of days between two dates in the most complex way imaginable:

ANTHROPIC_API_KEY="sk-ant-..." \
uv run --with pydantic-ai python -c '
import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerStdio

server = MCPServerStdio(
    "deno",
    args=[
        "run",
        "-N",
        "-R=node_modules",
        "-W=node_modules",
        "--node-modules-dir=auto",
        "jsr:@pydantic/mcp-run-python",
        "stdio",
    ],
)
agent = Agent("claude-3-5-haiku-latest", mcp_servers=[server])

async def main():
    async with agent.run_mcp_servers():
        result = await agent.run("How many days between 2000-01-01 and 2025-03-18?")
    print(result.output)

asyncio.run(main())'

I ran that just now and got:

The number of days between January 1st, 2000 and March 18th, 2025 is 9,208 days.

I thoroughly enjoy how tools like uv and Deno enable throwing together shell one-liner demos like this one.

Here's an extended version of this example which adds pretty-printed logging of the messages exchanged with the LLM to illustrate exactly what happened. The most important piece is this tool call where Claude 3.5 Haiku asks for Python code to be executed my the MCP server:

ToolCallPart(
    tool_name='run_python_code',
    args={
        'python_code': (
            'from datetime import date\n'
            '\n'
            'date1 = date(2000, 1, 1)\n'
            'date2 = date(2025, 3, 18)\n'
            '\n'
            'days_between = (date2 - date1).days\n'
            'print(f"Number of days between {date1} and {date2}: {days_between}")'
        ),
    },
    tool_call_id='toolu_01TXXnQ5mC4ry42DrM1jPaza',
    part_kind='tool-call',
)

I also managed to run it against Mistral Small 3.1 (15GB) running locally using Ollama (I had to add "Use your python tool" to the prompt to get it to work):

ollama pull mistral-small3.1:24b

uv run --with devtools --with pydantic-ai python -c '
import asyncio
from devtools import pprint
from pydantic_ai import Agent, capture_run_messages
from pydantic_ai.models.openai import OpenAIModel
from pydantic_ai.providers.openai import OpenAIProvider
from pydantic_ai.mcp import MCPServerStdio

server = MCPServerStdio(
    "deno",
    args=[
        "run",
        "-N",
        "-R=node_modules",
        "-W=node_modules",
        "--node-modules-dir=auto",
        "jsr:@pydantic/mcp-run-python",
        "stdio",
    ],
)

agent = Agent( 
    OpenAIModel(                          
        model_name="mistral-small3.1:latest",
        provider=OpenAIProvider(base_url="http://localhost:11434/v1"),                
    ),            
    mcp_servers=[server],
)

async def main():
    with capture_run_messages() as messages:
        async with agent.run_mcp_servers():
            result = await agent.run("How many days between 2000-01-01 and 2025-03-18? Use your python tool.")
    pprint(messages)
    print(result.output)

asyncio.run(main())'

Here's the full output including the debug logs.

# 4:51 am / deno, pydantic, uv, sandboxing, llm-tool-use, ai, llms, model-context-protocol, python, generative-ai, mistral, ollama, claude

Gemma 3 QAT Models. Interesting release from Google, as a follow-up to Gemma 3 from last month:

To make Gemma 3 even more accessible, we are announcing new versions optimized with Quantization-Aware Training (QAT) that dramatically reduces memory requirements while maintaining high quality. This enables you to run powerful models like Gemma 3 27B locally on consumer-grade GPUs like the NVIDIA RTX 3090.

I wasn't previously aware of Quantization-Aware Training but it turns out to be quite an established pattern now, supported in both Tensorflow and PyTorch.

Google report model size drops from BF16 to int4 for the following models:

• Gemma 3 27B: 54GB to 14.1GB
• Gemma 3 12B: 24GB to 6.6GB
• Gemma 3 4B: 8GB to 2.6GB
• Gemma 3 1B: 2GB to 0.5GB

They partnered with Ollama, LM Studio, MLX (here's their collection) and llama.cpp for this release - I'd love to see more AI labs following their example.

The Ollama model version picker currently hides them behind "View all" option, so here are the direct links:

• gemma3:1b-it-qat - 1GB
• gemma3:4b-it-qat - 4GB
• gemma3:12b-it-qat - 8.9GB
• gemma3:27b-it-qat - 18GB

I fetched that largest model with:

ollama pull gemma3:27b-it-qat

And now I'm trying it out with llm-ollama:

llm -m gemma3:27b-it-qat "impress me with some physics"

I got a pretty great response!

Update: Having spent a while putting it through its paces via Open WebUI and Tailscale to access my laptop from my phone I think this may be my new favorite general-purpose local model. Ollama appears to use 22GB of RAM while the model is running, which leaves plenty on my 64GB machine for other applications.

I've also tried it via llm-mlx like this (downloading 16GB):

llm install llm-mlx
llm mlx download-model mlx-community/gemma-3-27b-it-qat-4bit
llm chat -m mlx-community/gemma-3-27b-it-qat-4bit

It feels a little faster with MLX and uses 15GB of memory according to Activity Monitor.

# 5:20 pm / llm, ai, ollama, llms, gemma, llm-release, google, generative-ai, tailscale, mlx, local-llms

Claude Code: Best practices for agentic coding (via) Extensive new documentation from Anthropic on how to get the best results out of their Claude Code CLI coding agent tool, which includes this fascinating tip:

We recommend using the word "think" to trigger extended thinking mode, which gives Claude additional computation time to evaluate alternatives more thoroughly. These specific phrases are mapped directly to increasing levels of thinking budget in the system: "think" < "think hard" < "think harder" < "ultrathink." Each level allocates progressively more thinking budget for Claude to use.

Apparently ultrathink is a magic word!

I was curious if this was a feature of the Claude model itself or Claude Code in particular. Claude Code isn't open source but you can view the obfuscated JavaScript for it, and make it a tiny bit less obfuscated by running it through Prettier. With Claude's help I used this recipe:

mkdir -p /tmp/claude-code-examine
cd /tmp/claude-code-examine
npm init -y
npm install @anthropic-ai/claude-code
cd node_modules/@anthropic-ai/claude-code
npx prettier --write cli.js

Then used ripgrep to search for "ultrathink":

rg ultrathink -C 30

And found this chunk of code:

let B = W.message.content.toLowerCase();
if (
  B.includes("think harder") ||
  B.includes("think intensely") ||
  B.includes("think longer") ||
  B.includes("think really hard") ||
  B.includes("think super hard") ||
  B.includes("think very hard") ||
  B.includes("ultrathink")
)
  return (
    l1("tengu_thinking", { tokenCount: 31999, messageId: Z, provider: G }),
    31999
  );
if (
  B.includes("think about it") ||
  B.includes("think a lot") ||
  B.includes("think deeply") ||
  B.includes("think hard") ||
  B.includes("think more") ||
  B.includes("megathink")
)
  return (
    l1("tengu_thinking", { tokenCount: 1e4, messageId: Z, provider: G }), 1e4
  );
if (B.includes("think"))
  return (
    l1("tengu_thinking", { tokenCount: 4000, messageId: Z, provider: G }),
    4000
  );

So yeah, it looks like "ultrathink" is a Claude Code feature - presumably that 31999 is a number that affects the token thinking budget, especially since "megathink" maps to 1e4 tokens (10,000) and just plain "think" maps to 4,000.

# 10:17 pm / anthropic, claude, ai-assisted-programming, llm-reasoning, generative-ai, ai, llms