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

141–150 of 738 posts

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

#141

Post by whateveracct »

torben-friis wrote: post #36

>A caveat: Lines of code is an imperfect measure, as it measures quantity over quality. So 8× lines of code/engineer/day in the second quarter of 2026 is almost certainly an overstatement of the true productivity gain. Nonetheless, it indicates an acceleration. At Anthropic, we don’t reward people for how many lines of code they write; rather, team members are producing more code simply because they’re using AI syste…

Yeah, they assume that "productivity = k * LOC" where k > 1

very flawed

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

#142

Post by trefoiled »

apsurd wrote: post #69
Aperocky wrote: post #65

Earlier quoted context omitted.

Because code used to be correlated with progress, it became almost a measurement in lieu. But realistically, the code is meaningless if it doesn't accomplish something, and that should remain the true bar of progress. For instance, if I churned out 20x more code, threw away 19x code with rewrites and reverts and discards and accomplished the same project to the same standard 70% faster, would I do it? Yes. The part t…

You're right, my gripe is specifically with code slinging that hits production end users. My background is in product so to your point, it's very unnerving to see a straight line being enthusiastically optimized for developers -> customer facing product outcomes. This is contentious because I'm not exactly advocating for arbitrary gate-keepers. The nuance is that building usable stuff is hard. And not a matter of shi…

Forget about the danger of a dev to customer pipeline with no product people in between, some of us are living with the reality of product to customer pipeline with no developers in between, and that's much more disturbing. Our CEO is now the top contributor to our codebase, and he's completely non-technical.

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

#143

Post by freejazz »

reasonableklout wrote: post #64
Upvoter33 wrote: post #48

I'm having a hard time putting much faith into posts like these, especially as they near IPO.

Putting faith into the claim that recursive self-improvement is close to happening, or that they will coordinate with other companies / the government when the time comes?

Both.

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

#144

Post by pragmatic »

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".

Somebody read/watched too much Casey Muratori.

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

#146

Post by rishabhaiover »

aleqs wrote: post #40

Okay, so anthropic has amazing AI which supposedly writes most of their code and can continuously improve... meanwhile they have outages on a regular basis, and any kind of long-running work will now consistently hit 'API Error: Server is temporarily limiting requests'. Not sure of this is intentional to force a reduction of token usage, but at this point I need to build around these throttling limits and outages wit…

you're conflating a compute problem with a code quality problem.

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

#147

Post by layer8 »

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".

> 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

That’s rather sickening.

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

#148

Post by rytill »

jcarver wrote: post #125
cpursley wrote: post #94

Earlier quoted context omitted.

A came here just to write: Pretty please let it churn for a few nights and redo Claude Code in Rust. Because the harness is very very good as are their models, but that node thing is a hog for no good reason at all.

[dead]

I checked out your agent and it looks pretty well designed. Congrats on starting to share it with others!

One thing I noticed: "Your Tools: Aether agents get tools exclusively via MCP servers." "...Aether ships with 1st-party MCPs for file system operations..."

Can you share your thoughts on why you decided to use MCP as the core tool abstraction? I have heard many decry MCP as being context-wasteful. Is this not the case with your agent?

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

#149

Post by selimthegrim »

8note wrote: post #106
sonink wrote: post #61

Broadly agree to this position - I think there are some people skeptical that Anthropic is doing this for regulatory capture - but I think there are being honest about they are seeing and how regulation should catch up. I for one, believe that we should pause all work on AI for the forseeable future. This is almost impossible to orchestrate - but we should still try nevertheless. Maybe we are not able to pause, but w…

no, it really doesnt. the end of humanity has a strong case for banning all burning of fossil fuels immediately the end of humanity as a sales tactic to increase your stock price does not these are companies working on their IPO to make sure they can get the best price, not people being honest about what they think lies ahead. if they were being honest about what lies ahead, they'd unilaterally stop training, and put…

So what you’re telling me is that EY was the clearest thinking one out of all of them?
Post reply on HN