kesor

Nice. I made a similar thing as a TamperMonkey script that I can turn on and off on any website, it even includes a speed-controlled-voice that can read it for me.

One small annoyance with your app is the instructions in the welcome were tiny. Took me well over a minute to figure out how to control the thing, until I finally found those small hand icons in the right corner. You should consider adding these to the first page of welcome using a large-er size or something.

Only the human did ask the agent to do so. That was the whole point of this exercise.

Start with writing software that has https://en.wikipedia.org/wiki/Poka-yoke in mind

Let me circle-back to you on that one.

Maybe in the circles you circled in ... where I am from, I never had anyone saying "belt-and-suspenders" or "load-bearing" or "boil the ocean" or "swing for the fences" when talking about engineering topics. The only one who I heard say "circle-back to you" was Psaki.

You get "Grok Build" (the CLI) that uses the Cursor and/or Grok 4.5 models when you buy SuperGrok, which is like $300/year. I don't know if there is a feature-to-feature comparison by anyone on this, but you can get access to these models with unmetered tokens with SuperGrok.

Couldn't get it into landscape mode. Useless.

That is what government is for. Protecting itself from citizens.

You didn't play long enough. There are layers and layers and layers of features in that game if you play for 10 minutes or more.

The art of writing clickbait article headlines:

- Use a word like "science" to lure in the geeks

- (you don't even need to know what science is, its ok)

- Some of the geeks will push your headline to top of HN just because it had the right word in it

- Put some filler about life being hard in the article, so those who actually read it have to waste ten minutes of their lives (proving your point).

- Profit and glory!

It depends how much of that is services. If the device is hardware constrained, having an option to boot into a different set of services can be useful. Like a way to have more than a single lean thing, instead of a single bloated one.

Originally the word "Kanban" was used by Toyota to describe their card system that helped them achieve several important things, one of them was to NOT work on too many things at once. The other one was to visualize the work. And in general Kanban was used to manage the flow of work so that defects don't get through.

This tool on the other hand is all about "jam as much work as you can come up with into being created in parallel". Obviously there is no managing of any flow of quality outputs, and no limiting of any work because you just shove everything into the agent and burn tokens like crazy.

Calling this a "Kanban" really irks me ... its like blasphemy or something.

It is a way to switch into a different configs. Just like when you switch to a new set of packages when you update your channels (or flake) and you get activated with the new versions. Same thing with specializations, just you can choose to have a different set of packages activated and enabled in each different specialization. Like having multiple different configs in one.

How does an AI finding a proof of a question that someone asked very long ago, is going to improve anyone's cognitive capabilities?

Human cognition improves the more you practice it. Not when you outsource it to machines that do the "cognition" for you.

It is just a Linux device. Other people will install NixOS on it anyway, and use specializations if the whole idea of swapping device roles in-and-out is viable. I don't really understand why would the team that already got a full plate decide to also invent a whole new Linux system while they're creating their hardware device.

Instead of re-inventing Linux distributions for FlipperOS on top of Debian. They should just choose to base it on NixOS which already has these "profiles" as a built-in feature called "Specializations" https://wiki.nixos.org/wiki/Specialisation

People have been sent to the gulag by the Canadian government as well, not too long ago. Governments are disgusting.

So you have some folders with markdown files ... which are insanely hard to query without a tool ... impossible to traverse via their relationships ... and you call that a graph database? WHAT?!

Clicked the link expecting to see some tool or method that actually allows graph-like queries and traversals on files in a file system, all I found was some rant about someone on the internet being wrong.

Waste of time.

160,000 if you take the revisions into account

I would argue that Desktop Linux finally took off because of Steam Proton, and because of Windows 10/11 and macOS starting version fartascular or whatever their versions are named.

OpenSCAD can load STLs and cut holes in them.

Diffusion models for images are already pretty much binary code generators. And we don't need to treat each bit individually, even in binary code there are whole segments that can be tokenized into a single token.

Regarding training, we have many binaries all around us, for many of them we also have the source code in whichever language. As a first step we can use the original source code and ask a third party model to explain what it does in English. Then use this English to train the binary programmer model. Eventually the binary programmer model can understand binaries directly and translate them to English for its own use, so with time, we might not even need binaries that have source code, we could narrate binaries directly.

Why would you think its more complex? There are less permutations of generating transistor on/off states than there are all the different programming languages in use that result in the exact same bits.

Who said that creating bits efficiently from English to be computed by CPUs or GPUs must be done with transformer architecture? Maybe it can be, maybe there are other ways of doing it that are better. The AI model architecture is not the focus of the discussion. It is the possibilities of how it can look like if we ask for some computation, and that computation appears without all the middle-men layers we have right now, English->Model->Computation, not English->Model->DSL->Compiler->Linker->Computation.

You are missing the whole point of the article.

You, like many others, seem to imply that humans write "good" code, but they absolutely do not--unless they are running some million dollar team with checks and cross checks and years of evolving the code over failures. I've tested every junior developer using simple Javascript leetcode quizes and they all produce erroneous spaghetti slop.

The difference is, we forgive humans for needing iteration. We expect them to get it wrong first, improve with feedback, and learn through debugging. But when AI writes imperfect code, you declare the entire approach fraudulent?

We shouldn't care about flawless one-shot generations. The value is in collapsing the time between idea and execution. If a model can give you a working draft in 3 seconds - even if it's 80% right - that's already a 10x shift in how we build software.

Don't confuse the present with the limit. Eventually, in not that many years, you'll vibe in English, and your AI co-dev will do the rest.

Why you hate on prose? This article has been a joy to read, unlike a lot of the other slop on the internet.

Binary bits are also a language. A structured language that transistor-based computers execute into some result we humans find valuable. Why wouldn't a model be able to write these binary instructions directly? Why do we need all these layers in between? We don't.

Probably because then it wouldn't be software anymore. That is because you will be required to do a physical process (print an integrated circuit) in order to use the functionality you created. It can definitely be done, but it takes it too far away from the idea the author expressed.

But I don't see a reason why the LLM shouldn't be writing binary CPU instructions directly. Or programming some FPGA directly. Why have the assembly language/compiler/linked in between? There is really no need.

We humans write some instructions in English. The LLM generates a working executable for us to use repeatedly in the future.

I also think it wouldn't be so hard to train such a model. We have plenty of executables with their source code in some other language available to us. We can annotate the original source code with a model that understands that language, get its descriptions in English, and train another model to use these descriptions for understanding the executable directly. With enough such samples we will be able to write executables by prompting.

I don't think there is a need for an output language here at all, the LLM can read and write bits into executables directly to flip transistors on and off. The real question is how the input language (i.e. prompts) look like. There is still a need for humans to describe concepts for the machine to code into the executable, because humans are the consumers of these systems.

Don't train them to emulate humans. Train them to emulate compilers instead.