Broccoli AI at its best 🥦

Practical AI: Machine Learning, Data Science, LLM

We discussed “🥦 Broccoli AI” a couple weeks ago, which is the kind of AI that is actually good/healthy for a real world business. Bengsoon Chuah, a data scientist working in the energy sector, joins us to discuss developing and deploying NLP pipelines in that environment. We talk about good/healthy ways of introducing AI in a company that uses on-prem infrastructure, has few data science professionals, and operates in high risk environments.

Join the discussion

Changelog++ members save 5 minutes on this episode because they made the ads disappear. Join today!

Sponsors:

• Intel Innovation 2024 – Early bird registration is now open for Intel Innovation 2024 in San Jose, CA! Learn more OR register
• Motific – Accelerate your GenAI adoption journey. Rapidly deliver trustworthy GenAI assistants. Learn more at motific.ai

Featuring:

• Bengsoon Chuah – Twitter, GitHub, LinkedIn
• Daniel Whitenack – Twitter, GitHub, Website

Show Notes:

• MLFlow
• Prefect
• DuckDB
• Agrilla

Something missing or broken? PRs welcome!

Chapter

1. Welcome to Practical AI (00:00:00)

2. Sponsor: Intel Innovation 2024 (00:00:44)

https://intel.com/innovation?regcode=CMCCHL&utm_campaign=Changelog

3. Data science in energy (00:02:47)

4. Types of data stored (00:06:24)

5. Unstructured data (00:09:49)

6. The coolest data science app (00:12:34)

7. The bootstrapping problem (00:14:45)

8. Labelling instructions (00:19:09)

9. What scale? (00:23:09)

10. Sponsor: Motific (00:27:46)

https://www.motific.ai/

11. Judging data labelling (00:29:53)

12. Shipping models (00:31:40)

13. Where does DuckDB fit? (00:35:48)

14. Big data is dead (00:37:46)

15. Upcoming changes (00:38:40)

16. Thanks for joining us! (00:41:06)

17. Outro (00:41:44)