This is pretty neat.

I am more used to uv than pixi or mise so it would be an easier addition to my workflow.

However I do think it would probably be nicer if this kind of approach used conda packages as a source of truth. So kind of like pixi but without pixi!

Sorry, just trying to understand. Why would I use this over duckdb. duckdb already has plugins for a lot of databases. Is the syntax the advantage?

ClickHouse also supports a lot of data sources and has a local mode where you just use a single binary with local-only access.

Coincidentally, I wrote an article today on how I use it for similar scenarios. It can fetch from S3, multiple databases at once, and so on.

And you get all the benefits of a database when you need to join or postprocess data from multiple sources.

https://rushter.com/blog/clickhouse-data-processing/

It's more of a common database cli/shell which uses a well defined, and fast, ADBC protocol. You are basically freed from DuckDB's internal handling/runtime of query for various databases. Not to mention, this has vastly more supported databases.

With databow, the query still runs on the target database (unline duckdb), but you get one consistent CLI across different databases: connection profiles, output formats, history, scripting, and import/export behavior.

This is genuinely useful for humans (For example, I regularly juggle 6-7 different database, oltp, olap, search and key-value mixed), and even more useful for AI coding agents, because they don't have to learn and juggle a different CLI and set of flags for every database.

FWIW duckdb's optimizer does actually push some of the query down into the target database such as selects and where clauses, which you definitely want in many cases.

It’s going to have a very big hill to climb if it’s playing in a space where duckdb already has a hold. Duck has probably been my favourite technology find in the last few years. Awesome tech.

I’ll still check this out though.

I agree

I think the advantage is simplicity. Why connect first to duckdb and attach the db when you can query it directly with ADBC which is guaranteed to be fast

You don’t need to connect to duckdb, it’s just a process that you spawn.

You spawn in memory instance of duckdb and connect to it.

duckdb relies on filter pushdowns that makes the reason harder to spot, but you don’t use sqlite to connect to database via JDBC protocol, are you?

This is my question too

I always feel like I want to use something like this, but then realize my NeoVim setup + tmux + Ghostty is good enough and I am not ready to learn a whole another system for modest gains.

The friction I have currently is obviously things like port forwarding, in app browser etc.

I keep thinking to try out cmux but haven't gotten around to it.

makes sense, well if you ever want to dabble, let us know how you like it :)

Funny that its hosted on vercel. Probably because its employee driven rather than top down. Saves all the bureaucracy to get someone to sign a budget item to buy a domain.

Not sure that site in itself is owned and operated by the Norwegian government.

Is this article really worth sharing? A speculative headline with no numbers, no estimates, 0 data.

Feels like click bait and HN is submitting to the bait.

Oh you want numbers?

Here’s a number: 3.5

That’s the number of years until we achieve AGI according to Sam Altman: https://techresearchonline.com/news/sam-altman-predicts-agi-...

This company’s current valuation is entirely speculative. So if you’re going to criticize the article, maybe direct some of that skepticism towards the company in question.

Isn’t it general knowledge AGI has been achieved ?

You don't need numbers when the person responsible for the numbers says they are bad.

The billions being thrown at openai and anthropic are speculative

Yeah I have always felt GPT 5.4 does too much. It is amazing at following instructions precisely but it convinces itself to do a bit too much.

I am surprised Gemini 3.1 Pro is so high up there. I have never managed to make it work reliably so maybe there's some metric not being covered here.

Is this guaranteed by the async specification? Or is this just current behavior which could be changed in a future update. Feels like a brittle dependency if its not part of the spec.

It's documented behavior for the low-level API (e.g. asyncio.call_soon https://docs.python.org/3/library/asyncio-eventloop.html#asy...). More broadly, this has been a stable behavior of the Python standard library for almost a decade now. If it does change, that would be a huge behavioral change that would come with plenty of warning and time for adjustment.

In my experience, developers who rely on precise and relatively obscure corner cases, tend to assume that they are more stable than they later prove to be. I've been that developer, and I've been burned because of it.

Even more painfully, I've been the maintenance programmer who was burned because some OTHER programmer trusted such a feature. And then it was my job to figure out the hidden assumption after it broke, long after the original programmer was gone. You know the old saying that you have to be twice as clever to debug code, as you need to be to write it? Debugging another person's clever and poorly commented tricks is no fun!

I'd therefore trust this feature a lot less than you appear to. I'd be tempted to instead wrap the existing loop with a new loop to which I can add instrumentation etc. It's more work. But if it breaks, it will be clear why it broke.

That gives me slightly more confidence but only slightly.

For example what happens if I use a different async backend like Tokio?

Haven't used it but have seen some online recommendations for gh-dash. https://github.com/dlvhdr/gh-dash

I don't get it. All these are provided by many different agent libs like langgraph, Pydantic AI etc. I thought DSPy was for prompt optimization but I could never wrap my head around that aspect since like Langchain, DSPy seems to hide stuff a bit too much.

So this article seems surprising since it emphasizes more the non prompt optimization aspects. If that was the selling point I would rather use something like Pydantic AI when I already use Pydantic for so much of the rest.

I think the reality is that prompt optimization is one of the only "legible benefits" (ie easy to understand why its valuable).

But I think it misses the point of what Dspy "is". It's less that Dspy is about prompt optimization and more that, Dspy encourages you to design your systems in a way that better _enables_ optimization.

You can apply the same principles without Dspy too :)

Yeah I have always struggled to figure out why I would use SQLModel.

Big fan of FastAPI but I think SQLModel leads to the wrong mental model that somehow db model and api schema are the same.

Therefore I insist on using SQLAlchemy for db models and pydantic for api schemas as a mental boundary.