> today, Anthropic engineers on average ship 8x as much code per quarter as they did from 2021-2025.
strongest argument for token limits that I can think of, right here.
When AI Builds Itself: Our progress toward recursive self-improvement
411–420 of 738 posts
Re: When AI Builds Itself: Our progress toward recursive self-improvement
#412Earlier quoted context omitted.
Maybe I'm looking through rose colored glasses, but software that writes itself seems like a pretty big breakthrough to me.
That goes straight to my point: then why hasn’t the miracle of automated coding led to breakthroughs outside of automated coding? If the only breakthrough is automated coding with no outside consequence then it’s just masturbation
What is your bar even? automated coding has changed the game already.
Re: When AI Builds Itself: Our progress toward recursive self-improvement
#413Earlier 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.
Care to explain how you'd engineer it instead?
A reminder that anthropic has great rust/go sdks that they could have written their own tui in.
Re: When AI Builds Itself: Our progress toward recursive self-improvement
#414"If it were possible to effectively slow the development of this technology to give ourselves more time to deal with its immense implications, we think that would likely be a good thing. But if a slowdown simply lets the least cautious actors catch up technologically, it could leave everyone less safe." How convenient for investors. They talk like they're a nonprofit instead of a VC-backed business chasing an IPO.
Anthropic is at least a Public Benefit Corporation, and likely the first serious test of how useful that distinction is for a hyperscale company building a product with potentially huge societal downsides.
Re: When AI Builds Itself: Our progress toward recursive self-improvement
#415Earlier quoted context omitted.
You still need wizards to cast the spells..
Not if you’re claiming that the spells, once cast, automatically get exponentially spellier until they awaken into a spell god, capable of literally anything, including casting more complicated spells than any wizard is capable of. If that were true, you’d have no need for wizards. The fact that wizards are still around means it’s probably bullshit.
Is it too much to ask that people read the article before commenting?
Re: When AI Builds Itself: Our progress toward recursive self-improvement
#416Earlier quoted context omitted.
I am doing a solo project that is pretty big, meaning it is not something I could vibe code. I can do alot with AI that I could never do on my own, but I am not seeing several mulitples improvement in my productivity. I spend so much time doing what I call "AI wrangling", trying to get it to do what I want. Claude is writing all the javscript and python code, but ultimately I am programming in English. What is good i…
I'm building a memory safe programming language with a declarative concurrency model that's close to release. There is ZERO chance I would ever be able to complete it on my own. I doubt it'll get traction, but if it doesn't, I am pretty confident a future language will take the ideas for polymorphic synchronization and profile-guided optimization. It has an easy version/mode of compilation that makes Rust's affine ow…
How do you know it’s actually memory safe?
Re: When AI Builds Itself: Our progress toward recursive self-improvement
#417Earlier quoted context omitted.
They forgot to add 'make it as simple as possible' in the prompt is one possible cause. On a more serious note using a react-like lib for TUI in the hope you'll share the codebase with the web version is a more likely explanation. Still not the best idea.
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.
Re: When AI Builds Itself: Our progress toward recursive self-improvement
#418What I can’t get over is that there have been exactly zero software breakthroughs since vibe coding started, other than vibe coding itself. Claude is amazing, that’s true. But if it was as amazing as this article implies, I’d expect some breakthrough outside of AI itself. Rewriting a Zig program in unsafe Rust? Not a breakthrough. Finding a bunch of security vulns? Maybe that’s sort of a breakthrough though it’s unde…
Vibe coding is the breakthrough. There's always been "no-code" solutions to problems in various business domains, but they were invariably janky, underpowered, and/or overpriced. Now we have a way for domain experts to go directly from ACTUAL natural language directly to implementation in a real programming language, fully automated, in minutes or hours. How is that not a science-fiction level breakthrough? In 2011 if anyone had said that would be possible "in 15 years", I think most professionals at the time would not have replied with "yeah it's coming but your timeline is off". It would have been "you have no fucking idea what you're talking about".
Re: When AI Builds Itself: Our progress toward recursive self-improvement
#419Earlier quoted context omitted.
I think that's a valid point. You could very well be right. But we're discussing whether we should close the barn door while the horse is three miles down the road.
You mean that self improving AI is very far away? I'm not sure how much I believe that now it's solving Erdos problems?
Brother I used to be a skeptic... using it at Google has been incredible.
Right now I'm only having to direct to enforce good taste. Write tests, don't write an unnecessary function.
It does everything else practically. Presubmit, debugging, commit message generation, commit approval... it's happening.
Re: When AI Builds Itself: Our progress toward recursive self-improvement
#420Earlier 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.
This is a decades-old design pattern when CPU >> IO. Emacs has been doing just that since the 80s, when people were complaining about "Eight Megs And Constantly Swapping". See "redisplay" [1] This minimizes screen flash. You can't rely on terminals doing double-buffering. [1] https://github.com/emacs-mirror/emacs/blob/c29071587c64efb30... or a more user-friendly overview, Daniel Colascione's seminal "Buttery Smooth E…
lol what? There are definitely ways to make non flashing terminal UIs without this total insanity.