Skip to content
Creating tested, reliable AI applications (Practical AI #295) episode artwork

Nov 13, 2024 50 min

Creating tested, reliable AI applications (Practical AI #295)

from Changelog Master Feed

It can be frustrating to get an AI application working amazingly well 80% of the time and failing miserably the other 20%. How can you close the gap and create something that you rely on? Chris and Daniel talk through this process, behavior testing, and the flow from prototype to production in this episode. They also talk a bit about the apparent slow down in the release of frontier models.

Episode details come from the podcast's RSS feed.

Embed this episode

Ready to play

Creating tested, reliable AI applications (Practical AI #295)

0:00 50:09

Chapters

  1. 0:00 Welcome to Practical AI
  2. 0:57 Sponsor: Fly
  3. 3:33 Thanksgiving preparations
  4. 4:57 Agents in production
  5. 6:27 AI ceiling & current hype
  6. 8:39 Level of transformation
  7. 10:49 Current models are mostly good enough
  8. 16:55 Sponsor: Timescale
  9. 19:34 Robust AI workflows
  10. 24:39 Finding the right workflow
  11. 30:47 Transition from notebook to code
  12. 34:06 Sponsor: Eight Sleep
  13. 36:44 Testing and integrating
  14. 40:07 Sketching out a good framework
  15. 47:23 Roles have shifted
  16. 49:20 Outro

No transcript yet.

Requests help us decide what to transcribe next.

Frequently asked questions

How long is this episode of Changelog Master Feed?

This episode is 50 minutes long.

When was this Changelog Master Feed episode published?

This episode was published on November 13, 2024.

Is there a transcript available for this episode?

Yes, a full transcript is available for this episode. You can read the complete transcript on the episode page.

Can I download this Changelog Master Feed episode?

Yes. Use the download control on the episode player to save the publisher-provided media file.