Congrats! Good luck!

A visitor came to our Lupine

World’s highest resolution video of a two qubit gate demonstrating phase kickback.

At times, but it is stilled filled to the top with quantum AI slop which drives me nuts.

We have reached the moon again, but still can’t reproduce quantum twitter :D

Saw a cool picture of the moon of the other site and made a meme

A configurable fidget spinner with 4 arms, each having 3 axis that each have 5 possible positions.

Out of the 244,140,625 possible configurations* she chose ψ**.
She’s gonna love quantum when she grows up :D

*laziliy assuming each arm is uniquely labeled.
**TBH she called it a sword

Gonna use that guy next time I give a talk on QKD 😍

4yo: where did all the dinosaurs go?
Me: an astroid hit earth and they all died.
4yo: ?
Me: … *realizing she meant the dinosaur toys that were on the windowsill which my wife had moved* oh

GitHub - DeDuckProject/stim-mcp Contribute to DeDuckProject/stim-mcp development by creating an account on GitHub.

BTW, if you wanna try it out - I've deployed the MCP to a server for minimal setup.
You just have to insert this URL into a new connector:
stim-mcp-5s3woqufqa-uc.a.run.app/mcp

github.com/DeDuckProjec...

Sure, maybe if you give it the right context (papers, examples, etc...) it could help. I think a challenge would be in more unconventional flows - e.g. some adaptiveness cannot be modeled and simulated in a single run..

Chuck Norris once created a general algorithm that determines whether any arbitrary program will eventually halt by kicking a Turing machine.

Chuck Norris cannot be simulated classically.

Chuck Norris commutes with every operator but he is not the identity.

Chuck Norris is so big that you can measure his position and momentum simultaneously.

Chuck Norris once sneezed distilled magic states.

Chuck Norris can clone a qubit iff he knows the state of that qubit.

Chuck Norris can violate a Bell inequality by hand.

Chuck Norris doesn’t visit the church of the larger Hilbert space; the church visits him.

When you apply a controlled-chuck-norris gate on a pair qubits - the control qubit is affected.

(Regardless of whether the target qubit is an eigenstate of Chuck Norris)

Yeah, I believe it would be able to handle that. But I have no experience with asking to to create such circuits. Should they be more complex than error correction codes for e.g?

Window shows Claude chat the uses the Stim-MCP. ###### Left side (chat): show me how the logical error changes as I use larger and larger surface codes. Mar 17 I'll build rotated surface codes for distances 3, 5, 7, and 9, inject depolarizing noise, and sample logical error rates. Let me run them one by one. Create circuit Create circuit Let me use Stim's proper surface code format with detectors and observables so we get actual logical error rates: Used stim-quantum integration Used stim-quantum integration Good, d=3 logical error rate ≈ 0.622%. Now let me use Stim's built-in surface code generator for cleaner, properly structured circuits for all distances: Used stim-quantum integration Used stim-quantum integration The X-ancilla measurement rates ~50% means the H gates are putting them into superposition before measurement without proper reset into the right basis. Let me take the cleaner approach — use the well-known Stim surface code circuit format that's guaranteed correct: ... ###### Right side (preview): *shows some output plots from later in that conversation* Surface Code Scaling — Simulation vs. Google Hardware, with Willow-matched noise Stim v1.15 · rotated_memory_z · MWPM decoding (pymatching) · 10 rounds · 200k–2M shots Google 2023: Sycamore · Nature 614, 676–681 | Google 2024: Willow · Nature Dec 2024 / arXiv:2408.13687

Been messing around with creating MCPs that let LLMs run quantum tools like Stim or Microsoft QRE.

I wanna see if we can get reliable and interesting results, even for exploration. If you favorite LLM would know how to use these, what would you ask it?

Curious to get any feedback.

I am happy to share an important achievement:
I can tell my family “can everyone just DECREASE the entropy for a few minutes?” and they don’t look at me as if i’m crazy!

Monogamy of Entanglement posting

In quantum information theory, we don't say "I love you", we say "Our correlation is so strong that the Coffman-Kundu-Wootters inequality prevents me from being entangled with any other subsystem", and I think that's beautiful.

Is 31 missing by design?

🤣

Preparing for her talk in QIP 2046

Congrats Marco, that’s awesome!

This is not just an advantage; it’s a game changer.

To be completely honest I just used one cucumber there, and I couldn’t fit all that inside 😅