998: In Case You Missed It in May 2026
In this month’s episode of ICYMI, Jon Krohn explores how AI agents are simultaneously creating new risks and unlocking powerful new ways of working with data. Hear from Anneka Gupta, Cal Al-Dhubaib, Trevor Manz, Jazmia Henry, Jeremy Mumford, and Jacob Miller, discussing why the old cybersecurity playbook breaks down in the age of Claude Mythos, how the notebook became an AI agent’s working memory, what it really takes to build a foundation model from scratch, and why failing slowly is the most expensive mistake an AI team can make.
Additional materials: www.superdatascience.com/998
Interested in sponsoring a SuperDataScience Podcast episode? Email natalie@superdatascience.com for sponsorship information.
In this episode you will learn:
(00:40) Why Claude Mythos Changes Everything About Cybersecurity
(08:11) Why Your Notebook Should Be Your Agent’s Working Memory
(13:19) What It Actually Takes to Build a Foundation Model From Scratch
(20:46) Failing Slowly Is the Most Expensive AI Mistake
991: Pair Programming with AI in Your Python Notebook, with Dr. Trevor Manz
Dr. Trevor Manz of Marimo talks to Jon Krohn about Marimo Pair, an open-source agent skill that teaches coding agents like Claude Code how to drive a reactive Python notebook, reading cell state, running Python in the kernel, taking screenshots of cells, and iterating on data tasks the way agents iterate on traditional software. Trevor also unpacks recursive language models, his AnyWidget project that bridges Python and the web, and his journey from a Wisconsin small town and Harvard bioinformatics research to founding-engineer life at Marimo. Listen to the episode to hear why no matter where AI takes us, curiosity and going deep on a topic will always be valuable.
Additional materials: www.superdatascience.com/991
Interested in sponsoring a SuperDataScience Podcast episode? Email natalie@superdatascience.com for sponsorship information.
In this episode you will learn:
(07:04) What Marimo Pair is and how it teaches agents to use notebooks as a tool
(13:03) How agent skills work as folders of markdown files
(24:15) Trevor's day-to-day workflow combining Claude Code and Marimo Pair
(31:51) Recursive language models and why they could be the future of agentic reasoning
(57:33) Career advice on curiosity, going deep, and becoming a domain expert
Agentic Data Science Pair Programming With marimo pair
<p>How do you add agent skills to your data science workflow? How can a coding agent assist with data wrangling and research? This week on the show, Trevor Manz from marimo joins us to discuss marimo pair.</p>
<p>Trevor is a founding engineer at marimo, where he’s been working on integrating LLM tools with marimo. We discuss the balancing act of building a skill and determining how to give an agent access to all the variables in a notebook. He shares how they built a specialized reactive REPL that eliminates hidden state and allows the agent to continue constructing a reproducible Python program.</p>
<p>We dig into installing and getting started with marimo pair. Trevor also covers several of the tasks an agent can tackle in a data science workflow.</p>
<div class="alert alert-primary" role="alert">
<p><strong>Video Course Spotlight:</strong> <a href="https://realpython.com/courses/getting-started-with-marimo-notebooks/">Getting Started With marimo Notebooks</a></p>
<p>Discover how marimo notebook simplifies coding with reactive updates, UI elements, and sandboxing for safe, sharable notebooks.</p>
</div>
<p>Topics:</p>
<ul>
<li>00:00:00 – Introduction</li>
<li>00:02:26 – Trevor’s role at marimo</li>
<li>00:03:08 – Current AI tools in marimo</li>
<li>00:06:26 – Describing marimo notebooks</li>
<li>00:10:11 – What is marimo pair?</li>
<li>00:18:49 – Building an agent skill</li>
<li>00:27:34 – Setup & installation</li>
<li>00:31:16 – Video Course Spotlight</li>
<li>00:32:42 – Examples of EDA and data wrangling</li>
<li>00:45:46 – Experimenting inside of a notebook</li>
<li>00:50:40 – Managing context</li>
<li>00:53:25 – Accessing additional libraries</li>
<li>00:57:16 – Recent tools and updates from the marimo community</li>
<li>00:59:31 – What are you excited about in the world of Python?</li>
<li>01:01:10 – What do you want to learn next?</li>
<li>01:02:26 – How can people follow your work online?</li>
<li>01:03:13 – Thanks and goodbye</li>
</ul>
<p>Show Links:</p>
<ul>
<li><a href="https://marimo.io/blog/marimo-pair">Introducing marimo pair - marimo</a></li>
<li><a href="https://github.com/marimo-team/marimo-pair">marimo-pair: Drop agents inside running marimo notebook sessions</a></li>
<li><a href="https://news.ycombinator.com/item?id=47678844">Marimo pair – Reactive Python notebooks as environments for agents - Hacker News</a></li>
<li><a href="https://realpython.com/podcasts/rpp/230/">Episode #230: marimo: Reactive Notebooks and Deployable Web Apps in Python</a></li>
<li><a href="https://www.youtube.com/watch?v=6uaqtchDnoc">marimo Pair - YouTube</a></li>
<li><a href="https://www.youtube.com/watch?v=VKvjPJeNRPk">We gave Claude Access to All Python Variables - YouTube</a></li>
<li><a href="https://docs.marimo.io/guides/editor_features/ai_completion/">Using the marimo editor’s AI features - marimo</a></li>
<li><a href="https://github.com/astral-sh/ty">ty: An extremely fast Python type checker and language server, written in Rust.</a></li>
<li><a href="https://molab.marimo.io/notebooks">molab - marimo</a></li>
<li><a href="https://realpython.com/marimo-notebook/">marimo: A Reactive, Reproducible Notebook – Real Python</a></li>
<li><a href="https://realpython.com/courses/investigating-quasar-data-polars-marimo-notebooks/">Investigating Quasar Data With Polars and Interactive marimo Notebooks – Real Python</a></li>
<li><a href="https://marimo.io/blog">Blog - marimo</a></li>
<li><a href="https://www.linkedin.com/in/trevor-manz/">Trevor Manz - LinkedIn</a></li>
<li><a href="https://bsky.app/profile/manzt.sh">trevor manz (@manzt.sh) — Bluesky</a></li>
</ul>
<p>Level up your Python skills with our expert-led courses:</p>
<ul>
<li><a href="https://realpython.com/courses/investigating-quasar-data-polars-marimo-notebooks/">Investigating Quasar Data With Polars and Interactive marimo Notebooks</a></li>
<li><a href="https://realpython.com/courses/getting-started-claude-code/">Getting Started With Claude Code</a></li>
<li><a href="https://realpython.com/courses/getting-started-with-marimo-notebooks/">Getting Started With marimo Notebooks</a></li>
</ul> <p><a rel="payment" href="https://realpython.com/join">Support the podcast & join our community of Pythonistas</a></p>
#530: anywidget: Jupyter Widgets made easy
For years, building interactive widgets in Python notebooks meant wrestling with toolchains, platform quirks, and a mountain of JavaScript machinery. Most developers took one look and backed away slowly. Trevor Manz decided that barrier did not need to exist. His idea was simple: give Python users just enough JavaScript to unlock the web’s interactivity, without dragging along the rest of the web ecosystem. That idea became anywidget, and it is quickly becoming the quiet connective tissue of modern interactive computing. Today we dig into how it works, why it has taken off, and how it might change the way we explore data.
Episode sponsors
Seer: AI Debugging, Code talkpython26
PyCharm, code STRONGER PYTHON
Talk Python Courses
Links from the show
Trevor on GitHub: github.com
anywidget GitHub: github.com
Trevor's SciPy 2024 Talk: www.youtube.com
Marimo GitHub: github.com
Myst (Markdown docs): mystmd.org
Altair: altair-viz.github.io
DuckDB: duckdb.org
Mosaic: uwdata.github.io
ipywidgets: ipywidgets.readthedocs.io
Tension between Web and Data Sci Graphic: blobs.talkpython.fm
Quak: github.com
Walk through building a widget: anywidget.dev
Widget Gallery: anywidget.dev
Video: How do I anywidget?: www.youtube.com
PyCharm + PSF Fundraiser: pycharm-psf-2025 code STRONGER PYTHON
Watch this episode on YouTube: youtube.com
Episode #530 deep-dive: talkpython.fm/530
Episode transcripts: talkpython.fm
Theme Song: Developer Rap
🥁 Served in a Flask 🎸: talkpython.fm/flasksong
---== Don't be a stranger ==---
YouTube: youtube.com/@talkpython
Bluesky: @talkpython.fm
Mastodon: @talkpython@fosstodon.org
X.com: @talkpython
Michael on Bluesky: @mkennedy.codes
Michael on Mastodon: @mkennedy@fosstodon.org
Michael on X.com: @mkennedy