Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Launch HN: Nao Labs (YC X25) – Cursor for Data

news.ycombinator.com

Post reply on HN
Print view View original

41–50 of 68 posts

Re: Launch HN: Nao Labs (YC X25) – Cursor for Data

#43

Post by TheTaytay »

How much data is hitting your models/prompts? I am okay with you knowing about my schema, but a lot of warehouse data is sensitive data. I saw you have enterprise plans, and maybe that is my answer, but I’d love to know ahead of time if data/results are hitting your servers in addition to the code, or if it’s code-only.

Re: Launch HN: Nao Labs (YC X25) – Cursor for Data

#44

Post by paddy_m »

This looks like many LLM assisted data projects which help and are flexible, but aren't repeatable and aren't fast enough to be interactive. Nao is a good execution of the concept.

I built Buckaroo as a data table UI for Jupyter and Pandas/Polars, that first lets you look at the data in a modern performant table with histograms, formatting, and summary stats.

Yesterday I released autocleaning for Buckaroo. This looks at data and heuristically chooses cleaning methods with definite code. This is fast (less than 500ms). Multiple cleaning strategies can be cycled through and you can choose the best approach for your data. For the simple problems we shoudn't need to consult an LLM to do the obvious things.

All of this is open source and extensible.

[1] https://youtube.com/shorts/4Jz-Wgf3YDc

[2] https://github.com/paddymul/buckaroo

[3] https://marimo.io/p/@paddy-mullen/buckaroo-auto-cleaning Live WASM notebook that you can play with - no downloads or installs required

Re: Launch HN: Nao Labs (YC X25) – Cursor for Data

#45

Post by ClaireGz »

TheTaytay wrote: post #43

How much data is hitting your models/prompts? I am okay with you knowing about my schema, but a lot of warehouse data is sensitive data. I saw you have enterprise plans, and maybe that is my answer, but I’d love to know ahead of time if data/results are hitting your servers in addition to the code, or if it’s code-only.

The content of the data is never going to the models, unless you specifically grant access. Our server only store embeddings of your codebase and data schema. The content of the data is only accessed locally by your computer. When you ask our agent to run a query for you, it will execute it on your warehouse, then ask you for permission to read the result. If you don't allow it, you'll be able to preview it locally without sending it to the LLM. The enterprise version is for your if you want to be sure the prompts and context you send to nao don't go through a public LLM endpoint and get trained on.

Re: Launch HN: Nao Labs (YC X25) – Cursor for Data

#46

Post by ClaireGz »

paddy_m wrote: post #44

This looks like many LLM assisted data projects which help and are flexible, but aren't repeatable and aren't fast enough to be interactive. Nao is a good execution of the concept. I built Buckaroo as a data table UI for Jupyter and Pandas/Polars, that first lets you look at the data in a modern performant table with histograms, formatting, and summary stats. Yesterday I released autocleaning for Buckaroo. This looks…

Thanks for sharing. I like the view you built to visualize the profiling of your data, I think that's indeed key to understand your data.

Re: Launch HN: Nao Labs (YC X25) – Cursor for Data

#47

Post by paddy_m »

ClaireGz wrote: post #3
EliBullockPapa wrote: post #2

Cool idea! How did you train your tab model? Fill in the middle or is it based on edit history like cursor? Someone posted this yesterday and I found it fascinating https://www.coplay.dev/blog/a-brief-history-of-cursor-s-tab-...

Yes we use Fill in the middle models (Mistral and our own trained Qwen). And we feed it with your data context - we have our own SQL parser to feed you with the right data schema context depending on where your cursor is in the query.

I hadn't realized you trained your own model. That's an important differentiator. How do you get training data of schemas in the wild?

Re: Launch HN: Nao Labs (YC X25) – Cursor for Data

#48

Post by pdepip »

Congrats on the HN launch! Really excited to give this a try I think this could be a huge unlock for my team.

One quick issue - unable to connect to my postgres instance that requires SSL.

SSH tunneling seems to be broken as well because when the box is checked I am unable to select a private key path and the connect button is gone

Parsing DB URI would be a helpful feature as well!

Thanks so much, excited to get this up and running when everything is fixed!

Re: Launch HN: Nao Labs (YC X25) – Cursor for Data

#49

Post by pdepip »

pdepip wrote: post #48

Congrats on the HN launch! Really excited to give this a try I think this could be a huge unlock for my team. One quick issue - unable to connect to my postgres instance that requires SSL. SSH tunneling seems to be broken as well because when the box is checked I am unable to select a private key path and the connect button is gone Parsing DB URI would be a helpful feature as well! Thanks so much, excited to get this…

ignore the SSH tunneling, didn't see that i had to scroll...it's been a long week. regardless, SSL enabled connections would be huge
Post reply on HN