Keynote on using LLM-guided evolutionary program search (built on OpenEvolve) to discover 465 new bivariate-bicycle quantum LDPC codes, and what that stress test teaches about …
A new MCP server that enables AI agents to autonomously train reinforcement learning models for quantum circuit synthesis - including permutation, linear function, and Clifford …
The Curry–Howard correspondence—propositions as types, proofs as programs—offers a conceptual framework for understanding what's missing in current LLMs and what becomes possible …
You can now run the Qiskit Code Assistant locally easily. Download optimized models in GGUF format, install Ollama, and configure your VSCode or JupyterLab extension with a single …
We've upgraded the Qiskit Code Assistant! Last month, we introduced mistral-small-3.2-24b-qiskit, replacing granite-3.3-8b-qiskit, delivering better accuracy across key benchmarks …
Technical presentation on AI applications for Qiskit development at the BasQ Qiskit Fall Fest 2025 hackathon
Full-day tutorial at IEEE Quantum Week 2025 (QCE25) on using and training AI-powered transpiler passes in Qiskit for quantum circuit optimization, co-presented with David Kremer …
Released a new paper on a novel approach to train AI models that can write better quantum code using Qiskit. The approach uses quantum verification at the core, smart training …
Announcing the latest open-source LLM releases from the Qiskit Code Assistant team, featuring Qiskit 2.0 compatibility, enhanced text understanding, and new models including …
Family of open-source LLMs (8B–24B) for quantum code generation, plus the Qiskit HumanEval* benchmarks — 30K+ downloads on Hugging Face