The last mile of AI app development

There are a ton of problems around building LLM apps in production and the last mile of that problem. Travis Fischer, builder of open AI projects like @ChatGPTBot, joins us to talk through these problems (and how to overcome them). He helps us understand the hierarchy of complexity from simple prompting to augmentation, agents, and fine-tuning. Along the way we discuss the frontend developer community that is rapidly adopting AI technology via Typescript (not Python).

Leave us a comment

Changelog++ members save 1 minute on this episode because they made the ads disappear. Join today!

Sponsors:

• Fastly – Our bandwidth partner. Fastly powers fast, secure, and scalable digital experiences. Move beyond your content delivery network to their powerful edge cloud platform. Learn more at fastly.com
• Fly.io – The home of Changelog.com — Deploy your apps and databases close to your users. In minutes you can run your Ruby, Go, Node, Deno, Python, or Elixir app (and databases!) all over the world. No ops required. Learn more at fly.io/changelog and check out the speedrun in their docs.

Featuring:

• Travis Fischer – Twitter, GitHub
• Chris Benson – Twitter, GitHub, LinkedIn, Website
• Daniel Whitenack – Twitter, GitHub, Website

Show Notes:

• ChatGPT Hacker Community
• ChatGPTBot

Something missing or broken? PRs welcome!

Timestamps:

(00:00) - Intro
(00:43) - Travis Fischer & Stealth.ai
(07:01) - Surprising uses for models
(10:10) - Things to keep in mind
(14:13) - How to use these tools
(19:45) - Tips for evaluation
(23:48) - ABCs to riding the wave
(26:45) - The 2 AI communities
(31:16) - Multi-faceted AI?
(35:56) - Travis' controversial take
(37:26) - Outro