Episode 34 - AI Still Needs Humans in the Loop
About this episode
The episode discusses the necessity of human involvement in achieving consistent results from generative AI models.
Send a text When identical prompts yield different outputs and a request for "a cat running across the screen" generates four cylinders and a bobbing balloon, the non-deterministic nature of generative AI becomes impossible to ignore. Despite the power of these sophisticated models, we discovered that creating consistent, high-quality results demanded substantial human intervention – not less. Our journey moved from refining prompts to building extensive code example libraries, requiring th...
People in this episode
Hosts: Jon Gallagher, Logan Gallagher
Topics covered
- AI
- generative AI
- human intervention
- technology
- non-deterministic outputs
Keywords
- AI
- generative models
- human intervention
- non-deterministic
- prompt engineering
More episodes of Cloud Out Loud Podcast
- Open Source Reality Check
- Episode 36 - Open Source From Hackers to Kubernetes: How Open Source Evolved
- Episode 35: AI Hype vs. Reality: Rethinking Build vs. Buy
- Episode 33 - Creating an Animation Application using AI
- Episode 32 - Responsibility for Security in the Cloud
- Episode 31 - An AI Manifesto
Explore listener stats, chart rankings, contacts and more on the Cloud Out Loud Podcast podcast page.