mifydev

Great idea, but the landing page visuals is too cluttered, makes me want to have cursor for your website

Yeah, it should work for clis, even now. For larger codebases we just need to get two things right: - create good plans with the adequate tradeoffs for the type of service - make sure to have enough lints and tests to verify the completion end to end, either with browser, or with typechecking or like for c++ - complex static analysis.

We're constantly iterating on setup instructions and our repository analyzer, and during the integration we have a set of linters to prevent the model to generate completely broken code - it checks types, compiler errors for starters. The scope of the integration is explicitly limited, we make sure that the model doesn't do extra stuff.

We're working on adding more packages! Is there anything specific you need? We can add as well

We're working on adding popular libraries, but if you have a specific library, we'll be happy to add it!

Daily would be easy to add. We can technically add C++ library, but we don't have nearly enough linters in our agent even for me to trust it, so that's a task for the future!

Yup, that's the plan! We're starting with SDKs to nail code understanding and then we'll add browser tools for traversing web uis as part of integration

What do you prefer? We can use bun and provide a static binary https://bun.com/docs/bundler/executables, would that work for you?

It's only Next.js for now, we're expanding the library, what's the SDK you want to use? We can add it for you!

Meta is busy with this: https://news.ycombinator.com/item?id=45379514

I would love that, but it seems like they are not doing that either

But then you get annoying firmware providers like Broadcom who refuse to write OSS drivers for linux and a lot of work is being spent on the reverse engineering

OpenWRT is such a good os for a router - simple but configurable UI, works reliably, I wish router companies would just ship it by default

Congrats on the launch! I’m curious, do you have to store the tool inputs and outputs on the server side while either of the sides are waiting for response? I’m building a specialized coding agent for integrations and I had to avoid stateful api, because I don’t want to store user code.

Got it! In the future I think you can actually cache and reuse this code, and some flows will run automagically!

Looks great! How does it match intent to the set of tools, do you have a library of them?

Congrats on the launch, that looks dope! I'm curious, will this be able to run on an embedded robotics hardware?

I've just finished playing this awesome game again, it allows building computers as simple as playing factorio/satisfactory

Just visiting Japan, just realised that IC cards are super fast compared to London, crazy relevant article!

Yeah, the fair way would be show DOGE estimates for 10 years as well

It's /con/con all over again

The same should apply to configuration, we have prisma for sql, we should have something like this for JSONs, like https://typeconf.dev (I’m one of the founders)

I switched to Linux 12 years ago and still use it daily, although I think the problem is bigger than that. Even though hardware support is getting better, some bugs are lingering for years, and Wayland took such a long time to be a viable option. Now, as desktop became more complex to support, new platforms are coming, VR and mobile.

Mobile: I own Librem 5, and it was the biggest purchase disappointment I have ever had. I've been ridiculed by my friends while I was waiting for it for years, and when it was delivered, it was too outdated to use. The only silver lining from this is that mobile support exists in GNOME and KDE now. Hardware is still not there.

VR: I have not seen any viable option.

I'm optimising, and hoping that with AI it would be easier to support all of this, but now it looks kinda gloomy.

HN has declared supabase dead, how sad

This makes me wonder if this the way to do schema generation in Typescript. I’m working on Typeconf, and we have a separate step for translating Typespec schema to Typescript, it’ll be cool if we could just load typespec directly.

I feel like I should just be able to generate k8s configs from Typescript with Typeconf if I add all the types there, is anyone interested in this?

Oh, I didn’t know it was posted as recently as December, I just stumbled upon this again and assumed maybe not a lot of people have seen this recently

Years go by, but I always find myself getting back to this article, it's just the true essence of systems programming.

I've been thinking about this, to get rid of feeds I need something that will allow me to find posts and videos via related keywords. I want to be able to search for information by myself, but in this time, I need to be able to do it at scale. AI Agents that do research for me is a step in the right direction. Also, I think the platforms would resist this by trying to gatekeep information by all means necessary.

"Hot Shards in Your Area" - 10/10 heading