Agentic Coding For Scientists
A four-part series on using coding agents like Claude Code for scientific programming, covering fundamentals, workflows, best practices, and the human side of AI-assisted development.
The last five months with Claude Code have completely changed how we work.
matsen.group/agentic.html details:
• How agents work (& why it matters)
• Git Flow with agents
• Using agents for science
• The human-agent interface
Questions? What has your experience been?
13.11.2025 17:08
👍 14
🔁 6
💬 2
📌 1
So glad this is finally out. The method has been instrumental in allowing us to compress the AllTheBacteria data - ~2 million bacterial genomes shrink from 3Terabytes (gzipped) to 100Gb using phylogenetic compression. Great work by @brinda.eu
09.04.2025 22:27
👍 126
🔁 51
💬 4
📌 1
Now we just need an LLM to win the the literature prize #nobelprize
09.10.2024 12:32
👍 0
🔁 0
💬 0
📌 0
BWT construction and search at the terabase scale https://arxiv.org/abs/2409.00613 🧬🖥️ https://github.com/lh3/ropebwt3
04.09.2024 20:00
👍 6
🔁 1
💬 0
📌 0
crosswordgenius.com from www.unlikely.ai solves and explains cryptic clues using AI. When I give up on a clue and Google it I usually get sent there!
11.01.2024 22:29
👍 1
🔁 0
💬 0
📌 0
Great to see the study I worked on at Illumina's AI lab make it into Nature! www.nature.com/articles/s41... A lot of hard work by the lead authors, really pleased this has paid off. 🧬 🖥️
30.11.2023 10:44
👍 5
🔁 0
💬 0
📌 0
.@jnalanko.bsky.social and co. led groundbreaking work recently in terms of defining the SBWT & subset rank & select, and developing data structures for these. This new preprint provides reductions to standard rank & select, claiming similar space and 5-7x faster query arxiv.org/abs/2310.19702 🤯🧬🖥️
01.11.2023 03:28
👍 2
🔁 2
💬 0
📌 0