Simon Willison’s Weblog

Subscribe
Atom feed for mandelbrot

6 posts tagged “mandelbrot”

2025

Mandelbrot in x86 assembly by Claude. Inspired by a tweet asking if Claude knew x86 assembly, I decided to run a bit of an experiment.

I prompted Claude Sonnet 4:

Write me an ascii art mandelbrot fractal generator in x86 assembly

And got back code that looked... like assembly code I guess?

So I copied some jargon out of that response and asked:

I have some code written for x86-64 assembly using NASM syntax, targeting Linux (using system calls for output).

How can I run that on my Mac?

That gave me a Dockerfile.

I tried running it on my Mac and... it failed to compile.

So I fired up Claude Code (with the --dangerously-skip-permissions option) in that directory and told it what to run:

Run this: docker build -t myasm .

It started crunching. It read the errors, inspected the assembly code, made changes, tried running it again in a loop, added more comments...

Terminal window showing code diff for Mandelbrot fractal program. • Now I need to fix the Mandelbrot iteration logic as well. The current fixed-point arithmetic has issues: • Read(program.asm) └ Read 30 lines (Ctrl+r to expand) • The Mandelbrot iteration logic also has issues with fixed-point arithmetic. Let me fix this too: • Update(program.asm) └ Updated program.asm with 18 additions and 12 removals showing assembly code diff with line numbers 63-91, including removed lines marked in red for fixed point multiplication calculations and added lines in green with 64-bit arithmetic conversions, comments describing z_real and z_imag calculations, and mandel_done logic checks.

...and eventually produced an ASCII art image of a fractal! Claude Code proudly declared:

Success! The Docker container ran and generated a Mandelbrot set visualization using ASCII characters. The output shows all @ symbols, which indicates the algorithm is working but all points are inside the set (high iteration count). The program compiled and executed successfully on x86_64 architecture via emulation.

Yeah... I was not satisfied with an image that was entirely @ symbols! I said:

That is a bad result - it is just @ signs, I cannot see the fractal

Claude made a few more changes and gave me the result I wanted:

A terminal window showing a pleasing ASCII art Mandelbrot set, zoomed to the expected level

Here's the finished assembly code, the Dockerfile to run it on a Mac and the full transcript of the Claude Code session that got it there.

# 2nd July 2025, 4:35 am / mandelbrot, ai, generative-ai, llms, ai-assisted-programming, anthropic, claude, vibe-coding, claude-code

2024

Qwen2.5-Coder-32B is an LLM that can code well that runs on my Mac

Visit Qwen2.5-Coder-32B is an LLM that can code well that runs on my Mac

There’s a whole lot of buzz around the new Qwen2.5-Coder Series of open source (Apache 2.0 licensed) LLM releases from Alibaba’s Qwen research team. On first impression it looks like the buzz is well deserved.

[... 697 words]

11:37 pm / 12th November 2024 / mandelbrot, open-source, ai, generative-ai, local-llms, llms, ai-assisted-programming, llm, uv, qwen, mlx, ollama, pelican-riding-a-bicycle, paul-gauthier, llm-release

Claude 3.5 Sonnet. Anthropic released a new model this morning, and I think it's likely now the single best available LLM. Claude 3 Opus was already mostly on-par with GPT-4o, and the new 3.5 Sonnet scores higher than Opus on almost all of Anthropic's internal evals.

It's also twice the speed and one fifth of the price of Opus (it's the same price as the previous Claude 3 Sonnet). To compare:

  • gpt-4o: $5/million input tokens and $15/million output
  • Claude 3.5 Sonnet: $3/million input, $15/million output
  • Claude 3 Opus: $15/million input, $75/million output

Similar to Claude 3 Haiku then, which both under-cuts and out-performs OpenAI's GPT-3.5 model.

In addition to the new model, Anthropic also added a "artifacts" feature to their Claude web interface. The most exciting part of this is that any of the Claude models can now build and then render web pages and SPAs, directly in the Claude interface.

This means you can prompt them to e.g. "Build me a web app that teaches me about mandelbrot fractals, with interactive widgets" and they'll do exactly that - I tried that prompt on Claude 3.5 Sonnet earlier and the results were spectacular (video demo).

An unsurprising note at the end of the post:

To complete the Claude 3.5 model family, we’ll be releasing Claude 3.5 Haiku and Claude 3.5 Opus later this year.

If the pricing stays consistent with Claude 3, Claude 3.5 Haiku is going to be a very exciting model indeed.

# 20th June 2024, 6:01 pm / mandelbrot, ai, generative-ai, llms, anthropic, claude, vision-llms, claude-artifacts, claude-3-5-sonnet, llm-release

2023

textual-mandelbrot (via) I love this: run “pipx install textual-mandelbrot” and then “mandelexp” to get an interactive Mandelbrot fractal exploration interface right there in your terminal, built on top of Textual. The code for this is only 250 lines of Python and delightfully easy to follow.

# 1st April 2023, 7:23 pm / mandelbrot, python, textual

2017

SQLite Query Language: WITH clause. SQLite’s documentation on recursive CTEs starts out with some nice clear examples of tree traversal using a WITH statement, then gets into graphs, then goes way off the deep end with a Mandelbrot Set query and a query that can solve Soduku puzzles (“in less than 300 milliseconds on a modern workstation”).

# 26th November 2017, 7:23 am / mandelbrot, sql, sqlite

2009

Mandelbrot set in PostgreSQL. Surprisingly short SQL statement that produces an ASCII art Mandelbrot set.

# 13th August 2009, 2:23 pm / asciiart, fractals, mandelbrot, postgresql, sql

Related