Full-stack approach for effective AI agents

Practical AI: Machine Learning, Data Science, LLM

There’s a lot of hype about AI agents right now, but developing robust agents isn’t yet a reality in general. Imbue is leading the way towards more robust agents by taking a full-stack approach; from hardware innovations through to user interface. In this episode, Josh, Imbue’s CTO, tell us more about their approach and some of what they have learned along the way.

Leave us a comment

Changelog++ members save 2 minutes on this episode because they made the ads disappear. Join today!

Sponsors:

• Neo4j – Is your code getting dragged down by JOINs and long query times? The problem might be your database…Try simplifying the complex with graphs. Stop asking relational databases to do more than they were made for. Graphs work well for use cases with lots of data connections like supply chain, fraud detection, real-time analytics, and genAI. With Neo4j, you can code in your favorite programming language and against any driver. Plus, it’s easy to integrate into your tech stack.
• 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:

• Josh Albrecht – Twitter, LinkedIn
• Chris Benson – Twitter, GitHub, LinkedIn, Website
• Daniel Whitenack – Twitter, GitHub, Website

Show Notes:

• CARBS (Imbue’s cost-aware hyperparameter optimizer)
• Imbue paper on the stepwise nature of self-supervised learning
• A paper on initialization/feature learning co-authored by Jamie Simon, a member of Imbue’s technical team
• Imbue

Something missing or broken? PRs welcome!

अध्यायों

1. Welcome to Practical AI (00:00:00)

2. Josh Albrecht from Imbue (00:00:43)

3. Categorizing agents (00:04:50)

4. Making agents work (00:08:28)

5. Usecases for agents (00:11:47)

6. Full stack approach (00:13:56)

7. Research first (00:18:11)

8. Focusing on environments (00:20:55)

9. Fundamental laws to deep learning (00:24:11)

10. Sponsor: Neo4j (00:28:54)

https://www.neo4j.com/developer?utm_source=changelog&utm_medium=podcast&utm_campaign=practicalai

11. Engineering trust (00:30:02)

12. New interfaces (00:33:11)

13. Reviewable outputs (00:35:07)

14. Day to day coding with an agent (00:36:58)

15. Language context shifting (00:40:39)

16. Things to come (00:43:41)

17. Thanks for joining us! (00:45:50)

18. Outro (00:46:15)