blef

The ironic part of it is, that to my own experience and benchmarks Mistral is by far the worst model from frontier labs at tool calling followed closely by Gemini.

Looks awesome! If I may, could you add meters support?

but the thing is most of the time it's not about what the feature contains or is the feature working? (we have a live preview env where we can try the feature)

it's more how can we make sure in the thousands of rows/changes that we are reviewing every day we don't have invisible issues while keeping the code standards we expect

I am building nao, an open-source analytics agent. With nao you can connect all your sources of context (from warehouse to your knowledge base) using a CLI, and then you have an agent that sits on top of it.

You can use the agent from any client (web, Slack, Teams but also other harnesses).

We think most of data analytics work will be transformed (and is already being transformed) from SQL monkeys to chat to analyses, but all the UI/UX are not designed for this and this is what nao is, being open-source because knowing how the context is managed is key.

With nao you can have a conversation and then shared the output on the form of a story, that can be either static or live replacing what old dashboards were.

We are close to 1k stars on Github: https://github.com/getnao/nao

I really like the YouTube app to be honest and I really dislike the web version, so to me it does not work.

Reminds me https://www.agentsview.io/.

Ironic to see how popular this post is when you see the amount of generated AI companies are at YC (here I also take the blame).

Nonetheless I like this policy as well.

Thank you! I have to put the Storyboard online and a few screen of what you can do with it

I'm working most of my time on nao [1] (an open-source analytics agent).

With nao we are exploring the fact that agents are good to work with filesystems, so we help people getting the context into the filesystem and then you can plug our agent loop on top (on anything else).

The most exciting part is working with sandboxes and emulating filesystems. So at the moment the filesystem is local, but it could be a bucket or a database that we emulate as real filesystem for the agentic loop, all of this can also be mounted to sandboxes, and in the end you can do data transformations all in isolation with control on the context.

[1] https://github.com/getnao/nao

I feel it's a bit weird to redirect "Get started" to a Stripe page. When clicking on Get started i'd love to see more what's behind like it's used to be.

Nonetheless i like the idea.

Not sure about the naming, wouldn't something with Mistral naming better to understand what it is? Like Mistral Code or Mistral CLI or Clistral (lol)

The title would have been event better if: "I had ChatGPT analyze a decade of my Apple Watch data, then it called my doctor"

Supporting Iceberg is eventually having people leaving you because they have better elsewhere, but this is birectionnal, it means you can welcome people from Databricks because you have feature parity.

Feels old when you see how it played out to become SQL for everything in the data ecosystem lately.

Even though SQL as flaws, maybe a lot, it has one upside which is: it's so easy to onboard people on it, in the data ecosystem (warehousing etc.) it means that we can do way much stuff faster than before and hire less technical people, which is great

sad it's paywalled, but the title is interesting

I'm curious to see how you successfully got working well the types as I'm lost in the nightmare for a few days.

What could go wrong.

“888” is eight hours each of work, sleep and recreation, which is a great thing.

The ironic part of it is that most of the people doing 996 are building AI to replace humans work. And this is something that we don't talk about when speaking about 996. It's only a privilege, a lot of people would love to have normal job or a 996.

I come from Europe, I've had my high and lows when it comes to work hours, I was a consultant worked a lot, then a freelance and worked 2 day a week, now startup founder (YC) I don't count my hours but I'm close to working 6 days a week. To be honest the 4 years I worked 2 days a week were awesome and I'd wish everyone to reach that state where work is not the most important thing you do each week.

Except Databricks or Snowflake I have trouble seeing who in the data space would like to buy them. They are small among the big data companies ($1B rev)

And to save a click to people: "The React Foundation will be part of the Linux Foundation, which has long fostered a vendor-neutral environment for open source projects"

This is interesting. Funnily enough this is something that we also built in the tool I'm building called nao, which is a data editor for data teams. Because most of the SQL parsers aren't fault tolerant we had to develop our own fault-tolerant parser.

I really think what you showcase in the start of the article is the best thing, being able to statically highlight error in a text form for a user (or for a LLM) to iterate on the fixes is the best thing.

I'm one of the biggest fan of the Django ORM and I wish it would have won the battle over alembic/sqlalchemy that I dislike

paywall

Yes.

The onboarding flow is neat. I will give it a try over the next days. The local setup makes the computer heat a bit every 15 minutes, but it's ok

Looks like a scam / hack or something it says "Funding: $30,000,000 USD investment on standard YC terms" which is weird first and second the Github mail app doing this has been developed by a Github account that is 3 days old.

It's actually super clever. There is tho a bit of Javascript to make it work, but I learned something.

I'd say 'prioritization', especially in the beginning when users do not know exactly what they need/want.

Would be a perfect name if you could play every genre at once. Came for this, did not get this :'(

Funny but it lacks a few things to make it usable.

I'd love to know on what the semantic distance is computed. To make it more usable I'd love to be able to search for a company and see where in the graph it is, this way I could either look for my company or for a YC company that I know and then explore the proximity of this particular company.

Also I think we should be able to hover a dot to see the company