Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

When AI Builds Itself: Our progress toward recursive self-improvement

anthropic.com

Post reply on HN
Print view View original

451–460 of 738 posts

Re: When AI Builds Itself: Our progress toward recursive self-improvement

#451

Post by skydhash »

megous wrote: post #376
javcasas wrote: post #188

Earlier quoted context omitted.

> For each frame our pipeline constructs a scene graph with React then > -> layouts elements > -> rasterizes them to a 2d screen > -> diffs that against the previous screen > -> finally uses the diff to generate ANSI sequences to draw Yup. Overengineering.

React part maybe. The rest is what any TUI that's using ncurses would do. :) It really bothers me that most of the TUI harnesses are using 100% CPU quite a lot just printing stuff to terminal. Seems ridiculous. I guess it comes from syntax highlighting/formatting, which is probably not done incrementally, but over the entire so far displayed block of output, recomputed from the beginning for each new streamed in char…

> Terminal output itself is fast and consumes almost nothing. You can have 60fps terminal apps that update content every frame and that consume almost no CPU time.

The TUI mode is a client-server architecture. An analogy would be like an html page where all content is updated server side. Try to do 60 fps and you’ll have flickering as well.

Re: When AI Builds Itself: Our progress toward recursive self-improvement

#452

Post by uxhacker »

the_gipsy wrote: post #417
javcasas wrote: post #212

Earlier quoted context omitted.

React is not that stupid to re-render in a loop at 60fps and instead waits for changes to happen before re-rendering. It even batches changes and stuff.

You don't need React for reactive TUIs - at all. I can understand chosing React for web, but for a TUI it sounds like a really poor idea. And in practice we can see that the claude code TUI is also poor.

So how much more improvements are there for efficiency in the Claude code base if they are using react for a tui, in the rest of the code?

I also wonder about the wasted cycles and just the environmental damage caused by all these wasted cpu time . (Edited added a comma for clarity)

Re: When AI Builds Itself: Our progress toward recursive self-improvement

#453

Post by airstrike »

pizlonator wrote: post #313
joshuamcginnis wrote: post #305

Earlier quoted context omitted.

Massive productivity gains.

Yeah. To play devils advocate, computers didn’t translate to massive productivity gains until long after businesses adopted them. There was that quote from ’87: "you can see the computer age everywhere but in the productivity statistics" Maybe we’re seeing something like that right now with AI? Who knows man

Great comment. I think the answer is Jevons Paradox, as usual

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

Re: When AI Builds Itself: Our progress toward recursive self-improvement

#454

Post by airstrike »

lstodd wrote: post #226
javcasas wrote: post #215

Earlier quoted context omitted.

Nope. Used to render on the terminal like a game engine. https://x.com/trq212/status/2014051501786931427

I sorta remember Quake console running on an 486dx2 ..

LOL right? This is all that needs to be said about the engineering behind Claude Code

Re: When AI Builds Itself: Our progress toward recursive self-improvement

#455

Post by hahn-kev »

pizlonator wrote: post #295
wild_egg wrote: post #289

Earlier quoted context omitted.

What does a breakthrough look like?

Some examples: - The first web browser - the first web browser with images - typescript - react - rust - Fil-C - doom - quake - the anamorphic VM, and its follow-ups like HotSpot, and even competitors/copycats like J9, V8, JSC, etc - Fortnite battle royale - Roblox - thefacebook - ChatGPT - Claude code I know that’s quite a range and that’s intentional. Anyway, I think we’ll know it when we see it.

Reading through that list. None of those were breakthroughs when they first came out. It took time, in some cases a long time for them to become good.

Re: When AI Builds Itself: Our progress toward recursive self-improvement

#456

Post by shepherdjerred »

replwoacause wrote: post #154
airstrike wrote: post #112

Earlier quoted context omitted.

This might explain it, in the opposite way it was meant to: https://fxtwitter.com/trq212/status/2014051501786931427 > Most people's mental model of Claude Code is that "it's just a TUI" but it should really be closer to "a small game engine".

Why the hell does it need to be so complex? People have been making TUIs for decades. Did we need a small game engine to run claude code?

It is an excellent example of how LLMs let you try new ideas, even if they aren’t necessarily good ones

Re: When AI Builds Itself: Our progress toward recursive self-improvement

#457

Post by bicepjai »

My experience with Claude models starting from version 4.7 has led me to conclude that I would never trust Claude to produce error-free code. Given this baseline, I lack confidence in statements or cards (such as a 200-page document) of this nature.

Re: When AI Builds Itself: Our progress toward recursive self-improvement

#458

Post by yrds96 »

airstrike wrote: post #112
f311a wrote: post #88

Earlier quoted context omitted.

Infrastructure is a much harder problem. They can't even improve Claude Code, which eats 1GB+ of RAM. Meanwhile, my editor only consumes 80MB of RAM.

This might explain it, in the opposite way it was meant to: https://fxtwitter.com/trq212/status/2014051501786931427 > Most people's mental model of Claude Code is that "it's just a TUI" but it should really be closer to "a small game engine".

I can't still conceive the fact that a tool that only send/receive text from an external API consumes an absurd amount of RAM

Re: When AI Builds Itself: Our progress toward recursive self-improvement

#459

Post by skydhash »

fc417fc802 wrote: post #425
fluoridation wrote: post #245

Earlier quoted context omitted.

"Rasterizing" means just one thing in this context: to transform a data structure into an array of pixels. It seems absurd to do this, given that the next step must be to convert back from pixels to text data, but maybe they have some way to generate predictable sequences of pixels (e.g. the character "t" is always rendered as the same pattern of pixels), such that they're cheap to convert back. If they're doing anyt…

Yes, the much more plausible explanation is that the word rasterize was misused there. They are generating and diffing text data which has been a standard approach to drawing a TUI since the dawn of computing. It is not even remotely resource intensive.

> They are generating and diffing text data which has been a standard approach to drawing a TUI since the dawn of computing. It is not even remotely resource intensive

No one has ever done that. Even top[0], which does full screen refresh, clear the screen (if necessary) and write the new information (the period is in seconds, not ms). No need to diff. That would be like diffing a file, just to find which bytes to update.

[0]: https://cvsweb.openbsd.org/checkout/src/usr.bin/top/display....

Re: When AI Builds Itself: Our progress toward recursive self-improvement

#460

Post by mweidner »

sfink wrote: post #427
mweidner wrote: post #119

I fail to see how pursuing recursive self-improvement at full speed is compatible with Anthropic's stated goal of AI Safety. If nukes were not invented yet, would it really be a good idea to build and sell them as fast as possible (in peace time, no less)? I am not cynical enough to believe that Anthropic's warnings are pure marketing hype. Let's hope that it is instead overconfidence or the result of too much time t…

This was pretty directly addressed in the article: not doing it would only mean they'd fall behind whoever would. This is not peace time in the AI race. Whether you agree with that argument is another question.

Indeed, I do not buy this argument. Would China's progress be close to where it is today without the US labs' examples? Would any of this be happening if OpenAI had not created ChatGPT?
Post reply on HN