tomtomtom777

Absolutely horrifying.

Today they are bribing journalists to report on a bomb.

Tomorrow they will be bribing armies to bomb.

This needs to be banned.

> If the result is always provably correct it doesn't matter whether or not it's different at the code level. People interested in systems like this believe that the outcome of what the code does is infinity more important than the code itself.

If the spec is so complete that it covers everything, you might as well write the code.

The benefit of writing a spec and having the LLM code it, is that the LLM will fill in a lot of blanks. And it is this filling in of blanks that is non-deterministic.

> Effectively, the error is ignored although it might be logged. Thus our HTML is fine in practice.

That is not the right mindset to create good things. If it's an error, it's not fine.

Well, they do mention they are looking up whether it exists during the interview, so it's a forgivable mistake.

How did you know how well these results work?

You mention the quality several times in the article but it's not clear how this is verified. Do you have a set of known-location-ip-addresses around the world (apart from your home)? Or are we just assuming that latency is a good indicator?

Modern LLM's are very widely trained. You can simply tell it to speak like a tech bro.

I agree, and like to add,

> It is hands down good for code which is laborious or tedious to write, but once done, obviously correct or incorrect (with low effort inspection).

The problem here is, that it fills in gaps that shouldn't be there in the first place. Good code isn't laborious. Good code is small. We learn to avoid unnecessary abstractions. We learn to minimize "plumbing" such that the resulting code contains little more than clear and readable instructions of what you intend for the computer to do.

The perfect code is just as clear as the design document in describing the intentions, only using a computer language.

If someone is gaining super speeds by providing AI clear design documents compared to coding themselves, maybe they aren't coding the way they should.

Are we living on the same planet?

Surely the public discourse over the past decades has been steadily moving from substantive towards labeling each other villains, not the other way around.

Still, wouldn't a wifi meshnet be a better choice for these scenario's?

Nice; a way to also show the actual wrapping code would be nice.

I am assuming c is set to a canvas element and x is set to the context, but I can't find actual information on this.

> IMO these articles are akin to "Twitter in 200 lines of code!"

I don't think it serves the same purpose. Many people understand the difference between a 200 lines twitter prototype and the real deal.

But many of those may not understand what the LLM client tool does and how it relates to the LLM server. It is generally consumed as one magic black box.

This post isn't to tell us how everyone can build a production grade claude-code; it tells us what part is done by the CLI and what part is done by the LLM's which I think is a rather important ingredient in understanding the tools we are using, and how to use them.

I think integration into jq would be both powerful and sufficient.

This is neat. I didn't realize this was possible with the protocol. Thanks!

Instead of attachment, click on the second tab on top of the screen.

Yes, or it was still in memory from writing.

The numbers match quite nicely. 40gb program size minus 32gb RAM is 8gb, divided by 800mb/s makes 10 seconds.

It's quite often useful to have multiple tabs or panes in your terminal. Zellij does this. It's a terminal multiplexer, like tmux. Mostly just a bit more beginner-friendly and polished.

So obviously it's terminal-centric.

> I asked AI to explain it to me,

We all know how to do that, but that's not why were here.

The app doesn't even recognize geo:.. links, which makes degoogling rather hard.

You could argue that explicitly writing down the assumption would make it clearer to yourself and your reviewer that it might be overly optimistic.

Fascinating. It can see it work but I still can't really wrap my head around where the magic cycle length of 4 comes from.

If I understand it correctly, all programs were coded for unbounded growth; just accept more jobs/connections until it fails.

Obviously this is a bad idea. Even in Erlang's case because while some processes may continue to function, the behavior becomes utterly unpredictable.

In the real world, we would gracefully reject jobs/connections above a certain threshold.

This is exactly how I've learned to create my first Windows programs about 30 years ago, except that I'd use a C++ compiler.

I am not sure why but I believe writing C style code with a C++ compiler was how the windows API was documented to be used. I think Microsoft just went with the idea that C++ was an improved superset of C so should be used even for C-style code.

Agreed.

There is a good theory on why CEO's are paid more than they're worth called tournament theory.

A person in an upper layer of a hierarchical organization is paid for the value they provide PLUS an amount that incentivized anybody below them to reach that layer. If everybody is paid just for the value they provide, they wouldn't have a reason to try and reach higher layers and they would minimize work. After all, we cannot assume the value a person provides goes up in higher layers.

This additional pay bubbles up in larger organizations to exorbitant levels for CEO's.

Suckless has a beautiful coding philosophy and I wish all software was written with this in mind, but surely a window manager and X-menu aren't really the best showcases? These aren't the types of programs where complexity is the biggest enemy.

I'm not claiming I could write these tools as simple as these, but surely the importance of these paradigms arise when actual complicated software is needed?

From a profit maximization maybe.

But the government employs people. And in most of the civilized world, employing people comes with responsibilities over those people. For starters, the responsibility of not firing or changing terms that effects them on whim just for the sake of efficiency.

I don't no which country you are from but in the western world, if you compare countries by their tax rates, countries with high taxes [1] tend to score quite well on quality-of-life comparisons.

[1] https://en.wikipedia.org/wiki/List_of_sovereign_states_by_ta...

> It even solves the serialization issue of the difference between a "fixed-offset" timestamp (e.g. 2025-01-01T00:00+02:00) and one in a specific timezone (e.g. Europe/Paris).

Could you elaborate on that? What is the issue?

That is incorrect in this case. The "censoring" was done by the legislative branch, congress.

The "uncensoring" is done by the executive branch.

And when buffer overflows were (attempted to be) avoided by guestimating a large enough buffer size.

No. He did not abandon "World Chess". He is still an active player.

He chooses not to participate in the FIDE World Championship primarily because he doesn't like the format. He prefers a tournament format instead of a long 1-on-1 match against the running champion.