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

601–610 of 738 posts

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

#601

Post by bdamm »

4ffss wrote: post #383
bdamm wrote: post #326

Earlier quoted context omitted.

This is absolutely the right vision imo. Personally, I'm seeing massive improvements to my workflow and the quality of the product I'm shipping. I'm using AI to crank out far more tests than I used to be able to write, and I am using AI to analyze results with far more fidelity and speed than I could ever have done myself. That means I have more quality time. But this will change, because the meaning of software deve…

"That means I have more quality time." For now... the shareholders demand managers get the max out of every employee. Throw the force of competition etc into the mix and yeah labour isn't going to benefit all that much.

You are absolutely right. It will be a small window in the development business. Enjoy it if you can!

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

#603

Post by TeMPOraL »

danparsonson wrote: post #495
CamperBob2 wrote: post #225

Earlier quoted context omitted.

I declined to review it, stating that I couldn't possibly vet 40k lines of code Gee, that sounds like a job for Claude if there ever was one.

And how would you verify that the review was accurate?

Ask it to prove it.

My approach for AI-first code review, or really any kind of AI technical opinion, is that if the claim AI made is both important and not obviously true at a glance, it has to prove it to me, and keep trying until I'm convinced or can spot an obvious mistake in the proof.

With reviews, this is usually the case where AI is making a claim that something in the PR will fail because of some assumptions or behaviors in code outside of the PR - e.g. "this change will fail in scenario X, because foo is null in this case, because the SQL query doesn't populate it when bar == quux, and it gets propagated as null through the JSON deserialization (optional field)...", where all the SQL and JSON parsing was not part of the code under review, and "bar == quux" is some weird domain special case.

Stuff like this is both critical, and there's no way for me to judge it without an expensive context switch. So I learn to ask for a more detailed walk-through once, and if that doesn't make me "see" it, I just ask it to reproduce it with tests, and confirm it's a real problem. Reviewing the reproduction is usually enough for me to either "see it" or accept they're probably right and ask the author to recheck it.

(Why not jump straight to "reproduce it" for every finding? Because it still takes time to have AI do the repro. It's cheaper than a deep context switch, but not free.)

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

#606

Post by aswegs8 »

spaceman_2020 wrote: post #575
nostrebored wrote: post #566

Earlier quoted context omitted.

Do you not think that the allocation of human time is one of the world’s biggest problems?

It’s a problem for capitalists, not the people themselves The people want cheaper prices, affordable housing, affordable healthcare Capitalism has decided that these problems aren’t worth solving. Instead, we must optimize for spam and slop (and call it “distribution”)

I feel like one mental model here is that the attention is limited and under capitalism capital aggregates in the hands of few. Their attention is limited to things that immediately better their position, the most capital-efficient thing to do is to gather more capital.

Cheaper prices, affordable housing, affordable healthcare are less capital-efficient. If you're Walmart, sure, you would like to lower prices as much as possible. But your leverage really isn't as big as finance or tech. If you're a politician, you might also pursue those goals, but your attention and leverage really isn't as focused as that of the money machine.

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

#607

Post by verdverm »

TheRoque wrote: post #397
verdverm wrote: post #349

Earlier quoted context omitted.

It occurs to me this pattern might be the average code we humans have produced. We all have made those quick fixes, copy-pastas, and dirty hacks... they learned it somewhere! I also assume that some of the behavior is an artifact of their training regime.

So with LLM outputting average code, and people using LLM more and more, I guess the average code will become worse over time ?

There is a belief that everyone is just taking whatever the LLM (really agents now) outputs. This is not the case anywhere I work. We use human oversight to have it iteratively improve the code. The average quality is going up.

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

#608

Post by verdverm »

fooqux wrote: post #85
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…

Exactly. If AI is going to start being graded on how many LoC it generates- oh, I'm sorry, how much it "accelerates", than guess what newer models will start doing more of?

I'm actually hopeful that the recursive code training will improve quality over time. I'm definitely producing higher quality code, tests, and docs. It does take attention and oversight, iteration and refinement, one cannot just let these things loose on a code base and expect good things to happen. You have to leverage them to make the good things happen.

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

#609

Post by ezconnect »

nostrebored wrote: post #566
ElProlactin wrote: post #553

Earlier quoted context omitted.

Because they're going after the biggest problem of all first: labor costs. /s but not to a lot of people

Do you not think that the allocation of human time is one of the world’s biggest problems?

For the Capitalist crowd, YES it is the biggest cost. The next is energy. Imagine a world where your research and development is all AI and the production is all automated by robots. Instant product to sell to the masses who has no money because no one is working.

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

#610

Post by verdverm »

ponector wrote: post #582
nielsbot wrote: post #406

Earlier quoted context omitted.

Not advocating for AI code slop--but if AI coded software works correctly, maybe it doesn't matter? Except sometimes when a specialist will have to get involved. Not a perfect analogy, but most people don't write assembly these days--they have a compiler do that. Assembly still has a place, but it's a specialist task.

But the truth is: it doesn't work correctly. I see quality of software dropped significantly. At work we are integrating with third party platform to automate excel-powered calculations. It is awful. Rendering the table in browser takes 10s or one click on Export button will throw backend in OutOfMemory state.

Ai mirrors the code around it. So if there is bad code or good abstractions, it's going to do the same. Even with good code, it will do bad things, you have to remain in the loop and catch these. It can write good code, it just needs nudging.

I don't disagree there is a lot of slop being produced right now, but I'm still optimistic in the long-run.

Post reply on HN