#417: Test-Driven Prompt Engineering for LLMs with Promptimize

Talk Python To Me

Michael Kennedy

Technology

4.8 • 635 Ratings

🗓️ 30 May 2023

⏱️ 75 minutes

🔗️ Recording | iTunes | RSS

🧾️ Download transcript

Summary

Large language models and chat-based AIs are kind of mind blowing at the moment. Many of us are playing with them for working on code or just as a fun alternative to search. But others of us are building applications with AI at the core. And when doing that, the slightly unpredictable nature and probabilistic nature of LLMs make writing and testing Python code very tricky. Enter promptimize from Maxime Beauchemin and Preset. It's a framework for non- deterministic testing of LLMs inside our applications. Let's dive inside the AIs with Max.

Transcript

Click on a timestamp to play from that location

0:00.0	Large language models and chat-based AIs are kind of mind-blowing at the moment.
0:05.0	Many of us are playing with them for working on code or just as a fun alternative to search.
0:10.6	But others of us are building applications with AI at the core.
0:14.8	And when doing that, the slight unpredictable nature and probabilistic style of LLMs makes writing and testing Python code very tricky.
0:24.4	Interpromptimize from Maxine Bochman and preset.
0:28.1	It's a framework for non-deterministic testing of LLMs inside of our applications.
0:33.0	Let's dive inside the AIs with Max.
0:35.6	This is Talk Python, May, episode 417, recorded May 22nd, 2003.
0:54.0	Welcome to Talk Python, a weekly podcast on Python.
0:57.5	This is your host, Michael Kennedy.
0:59.4	Follow me on Macedon, where I'm at M. Kennedy, and follow the podcast using at TalkPython, both on Bostodon.org.
1:06.7	Be careful with impersonating accounts on other instances.
1:09.4	There are many.
1:10.5	Keep up with the show and listen to over seven years of past episodes at Talk Python.com.
1:15.6	We've started streaming most of our episodes live on YouTube.
1:19.5	Subscribe to our YouTube channel over at TalkPython.fm slash YouTube to get notified about upcoming shows and be part of that episode.
1:33.5	This episode is brought to you by JetBrains who encourage you to get work done with Pi Charm.
1:40.4	Download your free trial of PiCharm professional at Talkithon.fm.fm slash done dash with dash pie charm.
1:45.9	And it's brought to you by the compiler podcast from Red Hat. Listen to an episode of their podcast to demystify the tech industry over at Talkithon.fm slash compiler.
1:52.5	Max, welcome to Talk Python. Me. Well, it's good to be back on the show. And now I know it's live
1:57.6	too, so no mistake. So I'm going to try to not say anything outrageous.
2:02.2	But I've got the unfiltered version. So absolutely. Absolutely.
	...

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.