Hacker Newsnew | past | comments | ask | show | jobs | submit | themafia's commentslogin

> towards a future where they can build their own features directly, composed of our capabilities and served through our interfaces. that's what i'm focused on now. expect a note from me tomorrow.

These people are deranged or are flat out liars. Customers building "features directly." Yet somehow still trapped inside their walled garden? I wonder why they imagine they can cannibalize their legs but pretend they can save their arms in the long run.

They either believe they can have it both ways or they're simply milking a hot market right now and know one shoe or the other has to drop.


> At least allow us to use names instead of numbers.

Sure. Here's what that looked like:

https://en.wikipedia.org/wiki/Job_Control_Language


in spectrum.c

> Address bits for pixel (x, y): > * 010 Y7 Y6 Y2 Y1 Y0 | Y5 Y4 Y3 X7 X6 X5 X4 X3

Which is wrong. It's x4-x0. Comment does not match the code below.

> static inline uint16_t zx_pixel_addr(int y, int col) {

It computes a pixel address with 0x4000 added to it only to always subtract 0x4000 from it later. The ZX apparently has ROM at 0x0000..0x3fff necessitating the shift in general but not in this case in particular.

This and the other inline function next to it for attributes are only ever used once.

> During the > * 192 display scanlines, the ULA fetches screen data for 128 T-states per > * line.

Yep.. but..

> Instead of a 69,888-byte lookup table

How does that follow? The description completely forgets to mention that it's 192 scan lines + 64+56 border lines * 224 T-States.

I'm bored. This is a pretty muddy implementation. It reminds me of the way children play with Duplo blocks.


What happened with the wrong pixel layout is that the specification was wrong (the problem is that sub agents spawned recently by Claude Code are Haiuku session, their weakest model -- you can see the broken specification under spectrum-specs), it entered the code, caused a bug that Claude later fixed, without updating the comment. This actually somewhat shows that even under adversarial documentation it can fix the problem.

IMHO zx_pixel_addr() is not bad, makes sense in this case. I'm a lot more unhappy with the actual implementation of the screen -> RGB conversion that uses such function, which is not as fast as it could be. For instance my own zx2040 emulator video RAM to ST77xx display conversion (written by hand, also on GitHub) is more optimized in this case. But the fact to provide the absolute address in the video memory is ok, instead of the offset. Just design.

> This and the other inline function next to it for attributes are only ever used once.

I agree with that but honestly 90% of the developers work in this way. And LLMs have such style for this reason. I stile I dislike as well...

About the lookup table, the code that it uses in the end was a hint I provided to it, in zx_contend_delay(). The old code was correct but extremely memory wasteful (there are emulators really taking this path of the huge lookup table, maybe to avoid the division for maximum speed), and there was the full comment about the T-states, but after the code was changed this half-comment is bad and totally useless indeed. In the Spectrum emulator I provided a few hints. In the Z80, no hint at all.

If you check the code in general, the Z80 implementation for instance, it is solid work on average. Normally after using automatic programming in this way, I would ask the agent (and likely Codex as well) to check that the comments match the documentation. Here, since it is an experiment, I did zero refinements, to show what is the actual raw output you get. And it is not bad, I believe.

P.S. I see your comment greyed out, I didn't downvote you.


> It reminds me of the way children play with Duplo blocks.

WTF? I appreciate your technical expertise but you can't be aggressive like this on HN, and we've had to ask you this before: https://news.ycombinator.com/item?id=45663563.

If you'd please review https://news.ycombinator.com/newsguidelines.html and stick to the rules when posting here, we'd appreciate it.


> you can't be aggressive

I disagree that this is "aggressive." It's certainly opinionated. I think the AI does a bad job here and I'm attempting to express that in a humorous and qualified way.

> WTF?

You don't consider this to be "aggressive?"

> stick to the rules when posting here

Do you genuinely think I'm trying to be disruptive?


Ah - I interpreted the putdown as being about what antirez did, not what Claude did. It sounds like I misread that, and I apologize.

Even though I understand your sentiment, and think it is sincere, I think this is intellectually dishonest. Even though I have been programming since I was 16 (20 years), I still program like a child playing with Duplo blocks, when using a novel or otherwise unfamiliar technology. I bet that you do too. I also think that every programmer should play with their computers once in a while. Explore. Discover. Even if it means allowing yourself to be alienated from your means of production.

> they're not demanding that people proactively implement a system to prevent it from happening, are they?

What do you think a "background check" is?


Definitely not murder prevention

That's absolutely what they are. That and other crimes. That's why they're mandatory, by law, in certain industries. That's _precisely_ why we started using them: to prevent the easily preventable.

I suppose this logic stands in the way of a corporation getting what it wants and so it's automatically offensive to the HN "job seeking" crowd; however, even a basic reading of the history shows it's completely true.


> but do not have even a theory about how the behavior emerges

We fully do. There is a significant quality difference between English language output and other languages which lends a huge hint as to what is actually happening behind the scenes.

> but how exactly does anthill behavior come from ant behavior?

You can't smell what ants can. If you did I'm sure it would be evident.


Two very big revelations here that I would love to know more about:

1. Can you reveal "what's actually happening behind the scenes" beyond the hint you gave? I can't figure it out.

2. Can you explain how an ants sense of smell leads to anthills?


> 2. Can you explain how an ants sense of smell leads to anthills?

Ant 0: doesn’t seem to be dangerous here. I’ll drop a scent.

Ant 1: oh cool, a safe place. And I didn’t die either. I’ll reinforce that.

Ant 142,857,098,277: cool anthill.


The dynamics of ant nest creation are way more complicated than that. The evolved biological parallel of a procedural generation algorithm. In addition, the completed structure has to be compatible with the various programmed behaviors of the workers.

I am very curious about this significant hint, could you point me to some material?

> There is a significant quality difference between English language output and other languages

?


They're saying LLMs do better when outputting English than other languages, an assertion I'm not really able to test but have heard elsewhere.

and this is somehow not related to the size and availability of corpora in English?

No, I'm quite sure that's why it's better.

OK but then that goes back to their other assertion that it gives a huge hint at what is going on behind the scenes, is that huge hint just "more data gives better results!" if so, that doesn't seem at all important since that is the absolutely central idea of an LLM. That is not behind the scenes at all, that is the introduction to the play as written by the author.

Not your fault obviously, but they have not yet described what that huge hint is, and I'm just at the edge of my seat with anticipation here.


> The comments it offered were on the par of the best comments I’ve received on a paper in my entire academic career.

Sort of the lowest hanging fruit imaginable. Just because it became "fundamental" to the process doesn't mean it gained any quality.


> Change happens.

The low level tool that has served to rescue more systems than I can count does not need to "change" simply because "it happens, bro."

> while we can mechanistically

You can rule it out with process as well. As in "don't change what isn't broken."

> If they can introduce an RCE to Notepad

Then they clearly feel they have no viable competition. This is table stakes. Getting it wrong should lose you most of your customer base overnight. Companies actually used to _work_ this way.


If I told you to stop using computers, and then you won't have computer problems, I don't think you would find that particularly helpful or charitable either, would you?

What you find a trusty "low-level" tool is a demo application for a basic WYSIWYG text editor. They modernized it so that it remains being perceived that way, instead of letting it be increasingly misclassified as a legacy product for the enthusiast, like you just did.


I thought "basic WYSIWYG text editor" was more WordPad's lane, no? May it rest...

That was my first thought... Notepad is a plain text editor. Why add formatted text options when there's no good reason for it?

Plus, judging by the image, it doesn't look like there's controls to interact with the plain text markdown. It seems more like it's a "you can use markdown _codes_ to trigger text formatting. Jira has exactly this, and it's horrible.


> letting it be increasingly misclassified

"No, it's the customers who are wrong."


From their (supposed) perspective, yes. That's the idea I wanted to convey indeed.

The newest thing I've seen:

"compostable - except in CA"


Why? The microbes don't get along with sourdough starter bacteria?

It's because CA has stricter regulations about what can be labeled compostable. Whatever had this label was never compostable to begin with, but called itself that on a technicality.

yeah we took one of those cups and buried in a compost heap for a few years. it was not degraded in the slightest.

> Usa still don't even have universal social security

It does though. There are several programs, some administered by the federal government, and some by the states. We don't have "single payer" but we absolutely have "universal social security."

> and medications are overpriced 10 time more.

If you use the sticker price. Sure. It looks that way. If you use the actual pharmacy receipts the story is far different.


> to a declining, unstable empire

It's funny that we've wrapped the clock all the way around and people don't see Europe as the declining and unstable empires anymore.

> less like stable infrastructure

It's perfectly stable. The news makes a lot of money generating interesting in overstating this problem. The supreme court is designed for national stability. It is doing it's job. It just doesn't act _instantly_, and if you're aiming for actual stability, you don't want it to.


> The supreme court is designed for national stability.

On the contrary, I think that many of the rulings during this administration caused a lot of uncertainty among lawmakers


> The supreme court is designed for national stability.

lol my ass. We have a corrupt Adminstration with a corrupt Supreme Court. The only thing it's doing is making people less safe to enrich the people at the top. This kind of response is embarrassing.


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: