scrollaway

Caring for memory mattered more when memory was sparse.

But then again, it's crazy how people are disingenuous. You're in a thread about Bun being rewritten from a non-memory-safe to a memory-safe language and everyone's shitting on it because it's a useless rewrite. How does this mesh with what you say about caring for stability?

Using AI you can actually start caring about things such as memory, footprint, stability and speed because it's crazy cheap to start optimizing for this, when before you couldn't afford to make the tradeoff.

I have standards.

I have a literal Star Trek conception on my literal Star Trek device. Impossible to even think about how inconceivable this stuff was years ago.

And you’re complaining because they use react.

The epitome of entitlement, first world problems and privilege all together.

Yes I also used Bubbletea. I don’t know about ratatui but honestly I think the hate for react is very blind. It’s not like CC is shipping an embedded web browser. It’s a framework on top of an embedded language that has seen a crazy amount of optimisation.

Disingenuous, much? I've only ever had claude code crash once (after it decided to spawn like 12 subagents and got my laptop swapping like mad).

If you're crashing every 5 minutes, either you have a cursed build, or you need to do a memtest.

It sounds like you completely missed the point I was making: that actually implementing such a highly dynamic TUI application normally requires a significant amount of state tracking and it is significantly easier to write such apps using a functional, descriptive UI framework instead of something like ncurses.

Take it from someone who, in those 24 years, has written UIs in jquery, react and ncurses (and yeah I've tried out Ink and it's great).

"all the downsides that come with that" yeah well, while you're stuck implementing your app in the Best Possible Library, millions of people are happy using claude code and it's crazy useful.

And who put you in charge deciding that improving their zig codebase is the One True Way To Do Things?

Fuck, man, this used to be hacker news, a place where curiosity is rewarded.

Claude Code is able to hyperlink any kind of text, not just the native terminal emulator feature of hyperlinking anything starting with https://...

And your "it's just ANSI escape codes" is the weirdest take on any kind of software.

I have ~24 years of experience coding and the LAST thing I think about when opening claude code is "why is this written in react".

Tell you what I sometimes think about though: The fact it has clickable links and complex formatting rules for markdown, the most interactive and highest-quality clickable interface I've ever seen in a terminal, and somehow manages to work. That actually blows my mind.

THEN, I'm reminded that it's written in React, and I think "Huh, guess that does make it a ton easier than using ncurses or something."

And done.

It was fixed on May 21st, which is 6 days after it was merged to main, and is 6.5 weeks before the release.

Again, you are comparing things which are not comparable.

"Working on a feature" and "Working on a language-to-language port of 1M LOC" are NOT the same thing.

You're also still bringing up "regression per day", while ignoring the fact that without AI, this would have taken easily ~4000 days. Which is 1 regression per 0.003 calendar day. Not the same.

And you still aren't addressing sibling comments reminding you that these aren't shipped migrations. I'll second the comment asking you whether your code is always perfect first-shot, because if we're going to count those bugs, we might be well above your 1/day number.

Migrating a million lines of code is how many human-engineer-years worth of work? Some quick fermi estimates place it at between 15-100 years depending on how much automated tooling is used (without AI).

It really blows my mind how some AI naysayers like you fail the absolute basic common sense test of comparing the comparable. If you, without AI, merged nineteen regressions in 2 weeks, how much work has actually been done? How many features did you rewrite? How many refactors did you make and how difficult were they?

Insane...

Talk to a therapist.

I don't know why you're saying you're "tired of people's hateful bullshit". I originally responded that your point was off, and you're the one writing these comments: https://news.ycombinator.com/item?id=48886350

Take a breather, my guy. Stop saying in every comment that "you're done" and "this is your last response" and actually go touch a bit of grass. You do not owe anyone on this website a response, and the only thing your comments are for (when they're good and not hostile) is contributing to a discussion. Nobody here cares whether you respond or not.

Anyway, not to detract - this last comment was good. I just think maybe you're putting intent in people's mouths where there is none. For example, I certainly don't believe the bullshit Altman and Amodei are putting out. I just disagree the LLMs don't think.

And yes I also understand the math behind them. But it being math doesn't mean there cannot be emergent behaviour, just like there is emergent behaviour after the layers upon layers of biology in humans, resulting in thinking. "It's not magic, it's just [biology]" applies to us as well.

"But brains are the most complex machines in the universe" some might say -> Right, but who's to say the thinking we do requires machines as complex as our brains are? Our brains move muscles, help us breathe and manage millions of other invisible innate processes, many things LLMs do not need to do. And LLMs have a very, very deep access to and understanding of language, which is argued to be a significant contributor to how humans think (based on studies on nonverbal humans).

As soon as the math stops being done, the "thinking" stops. Does a brain ever stop thinking?

Right, so I understand your point in this and there's something to that, but it enters in how thinking is defined in both ways.

First, the calculation not running is at best equivalent to time stopping. It's not like the LLM actually sits there waiting for input. As you said: we continuously receive input, and we do so because our biology is built this way and we are damn energy efficient, so we can afford to continuously and asynchronously process that input. But this is not really related to the process of thinking itself.

So it comes down to what happens during the calculation. And Anthropic's published research on the J-space is pretty damning evidence, IMO, that thinking does happen during the calculation.

You phrased it better (and with a lot more patience) than I ever could muster.

So many people I meet are so deeply convinced LLMs absolutely cannot physically think, because they define "thinking" as "that thing you do with your human brain where neurons are involved", and they define "LLM thinking" as "that thing ChatGPT does where it says it's thinking but it's actually just detached inference".

The underlying assumption is usually two-fold:

1. That simulated thinking is not thinking.

2. That "LLM thinking" is always only defined as Chain of Thought.

Well, 1 is a pretty useless stance to have, because it removes space for any useful definition of what thinking is. And 2 is simply false, as presented by Anthropic here: https://www.anthropic.com/research/global-workspace

[flagged]

I hear he got burned pretty badly.

It's not low effort. I've noticed the blind AI hate on HN and I talked about it before. I think that "downvotes on the report of an experience" is good evidence of this. People don't want to hear that AI coding has positive outcomes.

I love how this completely personal opinion and experience is getting downvoted. The blind hate on anything AI on HN is mind boggling. True ostrich behaviour.

If you’re going to include AI training in costs, you should include education as part of the costs of an engineer …

Idk about you but this type of intensification of my work has been extremely good for my mental health, on all points:

1. I feel genuinely more productive, spending a lot less time on boilerplate and much more of my genuine time is spent thinking and communicating the thinking process.

2. I can take a ton of breaks, basically whenever I want. "Flow" is now entirely design flow and can be interrupted much more easily without damaging it.

3. If there is anything I actively dislike in my workflow or that makes me not enjoy my time... I can fix my workflow so that either I'm not the one doing it, or the item in question is no longer necessary.

AI is crazy. I get it, if you're at a shitty job that doesn't understand how to adapt well, it's tough... but if you're working on your own (like Simon does on this project), it's absolutely amazing and you're in full control of your life.

Vite Enterprise Edition Service Pack 3

This pointless test you're suggesting is a few countries removed from your initial suggestion, which was as a reminder: "The people using it or their employers just don't realize any competitor will be able to ask the LLM to replicate their product and it will copy the codebase they uploaded to them" (which, yes, is unfalsifiable given the search space)

I mean, are you seriously trying to back off that original ridiculous claim into a "code in the training data is more likely to appear in the output than code that isn't"? And I'm the fraud? As I said before, get over yourself.

There's open source ML&DL projects dating back 12 years on my github, I don't know what you're on about.

Regardless, your claim is "LLMs being able to one-shot any higher-order complexity is entirely dependent on it already being in the training data." which is currently unfalsifiable, and known by every AI researcher to be most likely wrong. You've also said it's "been demonstrated". So stop wasting people's time and link to the demonstration instead of hand-waving a "do it yourself you're smart".

Good lord, it's like talking to a bloody climate change denier, I swear.

I was working in machine learning before you were old enough to take programming classes.

https://github.com/jleclanche

As I said, I founded and run a AI lab. Now get over yourself.

If it has been demonstrated, you're welcome to cite a paper or even study of any kind. Right now, you're just guessing. (I head an AI lab, FYI)

This isn’t how training works.

Double-down on the thrill-seeking?

I'm just so tired of these lazy, worthless comments about any AI-written software.

Look, I've been writing open source software for 20+ years, and after getting seriously burned out by it, I picked it up again with Claude (proof: https://github.com/jleclanche)

I can tell you a few things from that:

1. I'm writing better software than before, because AI is less lazy than I am. It's not necessarily always smarter, but writing correct software has gotten so stupidly cheap that it doesn't make sense not to do things right... so when you tell AI to do things correctly, it tends to know what you're talking about.

2. I'm more curious than before, because AI gives me time to explore many paths, very fast. A project like this one, like someone else said elsewhere in the comments, is more about the journey than the destination.

There is no "write me an X11 server but do it in rust and post on hn" prompt that does the thing. There's a journey of building, learning, understanding.

I'm not saying the resulting software is particularly valuable, but the journey is. This is HN, and you're shitting on someone who is using the most powerful pieces of technology we've achieved to go on a journey of discovery of X11 internals for the past 2 months. It's just shameful.

And yeah, if I were the author, I'd run claude over all the transcripts and extract a story with what's been taught and learned throughout. But I'm not the author. Just someone enjoying living in absolute science fiction.

Ah yes, the famous zero-shot X11 server. Aren't you clever.

These "tricks" it knows IMO are a symptom of its own restrictions. Fable is an incredibly smart model, but it feels its own constraints and knows how to work around them in order to actually get to a result.

Fascinated to think about how it was trained...