To be fair, llama.cpp had this feature for over a year now. It just applies to GGUF.

Given the shortage of wafers, the wait might be long. I am however working on a bridging solution. Sime already showed Strix Halo clustering, I am working on something similar but with some pp boost.

Unfortunately, AMD dumped a great device with unfinished software stack, and the community is rolling with it, compared to the DGX Spark, which I think is more cluster friendly.

"Check your assumptions", will get a very long answer from a "thorough"LLM.

This amazing! I am definitely a target audience for this (I don't run any phone without at least unlocked bootloader, root and lsposed). So happy to see ROMs are coming to Android watches!

As someone who used duckdb but not shaper, what is shaper used for? The readme is scarce on details.

hi, dev building shaper here. shaper allows you to visualize data and build dashboards just by writing sql. the sql runs in duckdb so you can use all duckdb features. its for when you are looking for a minimal tool that allows you to just work in code. you can use shaper to build dashboards that you share internally or also for customer-facing dashboards you want to embed into another application.

Will it expose a visual query builder as metabase?

shaper leans into doing everything as code. instead of using a custom UI you can use your own editor and AI agent to generate dashboards for you. shaper is for people happy to use code. it doesn't try to provide self-serve functionality.

And I think that's exactly what makes it so clever. Three years ago, I would have considered this decision risky. But with the live sync feature and "just SQL" as the language for the dashboard builder, it's so powerful—thanks to Claude Code, for example!

It captured a bit the feeling of being at the start of the computer boom in 60s-70s. The partnernship between the 2 male protagonists was central till the end of show (evolving through different phases). The show was great, it went in very unexpected directions later on.

It's interesting to how they found out the "lifetime" of features is a feature by itself. Meta features is real.

It's not just that. Everyone is complacent with the utilization of AI agents. I have been using AI for coding for quite a while, and most of my "wasted" time is correcting its trajectory and guiding it through the thinking process. It's very fast iterations but it can easily go off track. Claude's family are pretty good at doing chained task, but still once the task becomes too big context wise, it's impossible to get back on track. Cost wise, it's cheaper than hiring skilled people, that's for sure.

Cost wise, doesn’t that depend on what you could be doing besides steering agents?

Isn't the quote something like: "If these LLMs are so good at producing products, where are all those products?"

Waiting for godot…

That's what LLMs enabled. Faster prototyping. Also lots of exposed servers and apps. It's never been more fun to be a cyber security researcher.

I think it just has been more fun being into computers overall!

It's interesting because if you're into computers it's more accessible than ever and there are more things you can mess with more cheaply than ever. I mean we have some real science fiction stuff going on. At the same time it's probably different for the newer generations. Computers were magical to me and a lot of that was because they were rare. Now they are everywhere, they are just a backdrop to everything else going on.

I agree, I remember when the feed forward NN were the shit! And now the LLMs are owning, I think this adoption pattern will start pulling a lot of innovations on other computer science fields. Networking, for example. But the ability to have that peer programer next to you makes it so much more fun to build, when before you had to spend a whole day debugging something, Claude now just helps you out and gives you time to build. Feels like long roadtrips with cruise control and lane keeping assist!

If you don't want the "hassle" of flag optimization when compiling binaries, CachyOS is basically Arch but with optimized binaries. Otherwise, Gentoo all the way, you just need a good machine.