AI-Assisted Programming for Physicists
Vibe coding is the new way to use Large Language Models (LLMs) to work on software, projects, and even scientific research itself. Rather than writing every line of code manually, you collaborate with AI systems that can generate, edit, debug, and refactor code based on natural language instructions.
In this seminar, we explore what vibe coding is, best practices for working with AI coding assistants, the tools available across different workflows, and critically — when these tools excel and when they fall short. You'll see real demonstrations of AI-assisted coding in action, from simple autocomplete to autonomous agents that can tackle complex multi-file projects.
Whether you're curious, skeptical, or already using these tools, this seminar provides a grounded, evidence-based look at the current state of AI-assisted programming and how it can fit into research workflows.
A hands-on introduction to AI coding tools, designed for physicists. No hype — just evidence and practical demonstrations.
Claude, ChatGPT, Gemini — copy-paste workflows and their use cases.
GitHub Copilot and Cursor autocomplete — inline suggestions and productivity.
Cursor agents and agentic workflows in the IDE.
Terminal-based autonomous agents for complex tasks.
GitHub Issues, PRs, and project-level AI automation.
Claude, ChatGPT, Gemini — copy-paste workflows. Good for exploration, quick questions, and one-off scripts. Breaks down for complex projects.
GitHub Copilot, Cursor autocomplete — inline suggestions as you type. Reduces boilerplate but requires constant attention.
Claude Code, Cursor Agent, Aider — delegate entire tasks. Think of it like working with a capable research assistant.
GitHub Issues + PRs with AI. Create issues, let agents implement, review PRs. Scales to large codebases.
Assistant Professor
Works on foundation models for particle physics (IceCube, LHC). Published papers on efficient language model training (BabyLlama). Used LLMs for coding before ChatGPT existed. Diehard Claude Code user.
Postdoc, ATLAS ML Coordinator
Lead ML efforts at ATLAS (CERN LHC experiment), 3 years of vibe coding fanaticism, user of LLMs for writing code, managing projects, writing grants, organizing entire life. Creator of chATLAS AI assistant for ATLAS collaboration.
Head of Subatomic Physics Section
Long-time AI/ML advocate, particle physicist with ATLAS and IceCube.
If you want to follow along during the demos:
Sign up for GitHub Education with your university email to get free Copilot access.
curl -fsSL https://claude.ai/install.sh | bashRequires Claude Pro subscription ($20/month) or Claude credentials.
No prior setup required to attend — you can just watch the demos.
Essential tools and resources for AI-assisted programming. Most of these are free for academics!
Get free access to GitHub Copilot, GitHub Pro, and many other developer tools with your academic email.
What you get:
How to apply: Visit education.github.com and sign up with your university email address. Approval usually takes 1-2 days.
Microsoft's popular code editor with extensive extension support.
Key features:
Download: code.visualstudio.com
AI-first code editor built on VSCode with advanced autocomplete and chat features.
Key features:
Pricing: Free tier available, Pro plan $20/month
Download: cursor.sh
Anthropic's official terminal-based AI coding assistant. Autonomous agent that can edit files, run commands, and complete complex tasks.
Key features:
Installation:
curl -fsSL https://claude.ai/install.sh | bashRequirements: Requires subscription to Claude Pro ($20/month) or Claude credentials. See code.claude.com/docs for details.
Ultra-fast Python package installer and resolver written in Rust. A modern replacement for pip and pip-tools.
Key features:
uv pip installInstallation:
curl -LsSf https://astral.sh/uv/install.sh | shLearn more: github.com/astral-sh/uv