Author(s): Serj Smorodinsky

Originally published on Towards AI.

Data science perspective

This member-only story is on us. Upgrade to access all of Medium.

This is my take, you don’t have to take it

If you think that a picture is worth 1000 words, then a video should be worth like a 100,000? Anyhow, you can watch me go over all of the sections live on my channel.

This is a power tool that lets you describe what you want and get it. What’s special about it? Why not continue using web based code assistance? Or just use a co-pilot?

Cursor AI allows you to stay within the IDE’s without ever wanting to leave.

It lets you choose the context you need, without copy pasting. It knows your whole project and understands its structure. It manipulates the files in an iterative way letting you reject and apply the changes visually by showing a diff (similar to code diff tools). Web based flow is great for quick patches but working in Cursor AI does feel like working with another person, for better and worse.

In the following blog I showcase 5 examples of how I am using it in my flow:

Staying in control by providing a specManipulating non-code files (.csvs, .txt). Bonus for data scientistsAsk to create tests even… Read the full blog for free on Medium.

Join thousands of data leaders on the AI newsletter. Join over 80,000 subscribers and keep up to date with the latest developments in AI. From research to projects and ideas. If you are building an AI startup, an AI-related product, or a service, we invite you to consider becoming a sponsor.

Published via Towards AI