#526: Building Data Science with Foundation LLM Models

Talk Python To Me

Michael Kennedy

Technology

4.8 • 642 Ratings

🗓️ 1 November 2025

⏱️ 67 minutes

🔗️ Recording | iTunes | RSS

🧾️ Download transcript

Summary

Today, we’re talking about building real AI products with foundation models. Not toy demos, not vibes. We’ll get into the boring dashboards that save launches, evals that change your mind, and the shift from analyst to AI app builder. Our guide is Hugo Bowne-Anderson, educator, podcaster, and data scientist, who’s been in the trenches from scalable Python to LLM apps. If you care about shipping LLM features without burning the house down, stick around.

Transcript

Click on a timestamp to play from that location

0:00.0	AI has changed how we write code and data science is right in the blast radius.
0:04.6	Today we move past autocomplete to systems that file PRs, comment in Slack, and even police
0:10.0	RCII.
0:11.1	Hugo Bound Anderson is back to map the new stack, when classic Pi data still wins, where
0:17.1	small local models beat the cloud, and how tests become your specs.
0:21.5	We dig into cursor and co-pilot, proactive agents, and practical patterns you can ship this week.
0:26.6	This episode is all about leveling up your data science workflow, not replacing it.
0:31.2	This is Talk Python to Me.
0:32.6	Episode 526 recorded October 7th, 2025.
0:39.3	Talk Python to me. Yeah, we ready to roll. Upgrading the code. No fear of getting old.
0:44.8	They sink in the air. New frameworks in sight. Geeky rap on deck. Quark crew. It's time to
0:50.2	unite. We started in pyramid. Cruise old school lanes, had that stable base.
0:55.0	Welcome to Talk Python to me, the number one podcast for Python developers and data scientists.
1:00.1	This is your host, Michael Kennedy. I'm a PSF fellow who's been coding for over 25 years.
1:05.9	Let's connect on social media. You'll find me and Talk Python on Mastodon, Blue Sky, and X. The social links are all in the show notes.
1:13.3	You can find over 10 years of past episodes at Talkbython.fm. And if you want to be part of the show,
1:19.3	you can join our recording live streams. That's right. We live streamed the raw, uncut version of
1:24.6	each episode on YouTube. Just visit Talkbython.fm slash YouTube to see the schedule of upcoming events.
1:31.5	And be sure to subscribe and press the bell so you'll get notified anytime
1:35.3	or recording. This episode is sponsored by Posit Connect from the makers of Shiny.
1:40.8	Publish, share, and deploy all of your data projects that you're creating using Python.
1:45.4	Streamlet, Dash, Shiny, Boca, Fast API, Flask, Quarto, reports, dashboards, and APIs.
	...

Please login to see the full transcript.

Previous episode | Next episode

Disclaimer: The podcast and artwork embedded on this page are from Michael Kennedy, and are the property of its owner and not affiliated with or endorsed by Tapesearch.

Generated transcripts are the property of Michael Kennedy and are distributed freely under the Fair Use doctrine. Transcripts generated by Tapesearch are not guaranteed to be accurate.