The Hard Problems™️ of Data Observability w/ Kevin Hu of Metaplane
The Analytics Engineering Podcast
00:00
Is There a Limit to Machine Learning?
For observability tools, i thinki one of the hard challenges is being able to use human time and attention effectively. We will need some annotation from real humans that understand whate the heck is going on. That's why we try an auto mate as much as possible and only get human feedback on the most important or uncertain anomalies. But you needn't put innotations to learn from humans to t actually improve the machine learning models.
Transcript
Play full episode
