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

The Tower Keeps Rising

lucumr.pocoo.org

Post reply on HN
Print view View original

81–90 of 280 posts

Re: The Tower Keeps Rising

#81

Post by tekacs »

conartist6 wrote: post #20
Animats wrote: post #13

Earlier quoted context omitted.

The upper bound on program complexity used to be the power of the human mind. "Vibe coding" can break through that barrier. But not because the problem being solved needs that complexity. Because the process does not drive itself towards compact abstractions. It's the AI-powered version of the scaling problem Brooks described back in "The Mythical Man-Month". The combinatoric problems get worse with scale. Concretely…

Why would it? It has optimized what it was built to optimize: this is the token-selling industry. Take note that the people hawking the dream of a gold rush are not actually mining but selling shovels

Labs are trying to make long-horizon work. Even if you're a coding agent, adding more and more surface area is distracting to that goal. There is reason that RL over long traces should, at least in principle, optimize for building in ways that help the result fit in the model's context window.

A meaningful risk of course is that the tools available to the model (ripgrep + fancier semantic approaches) allow it to do a good job of reasoning over things much larger than its context window, and so it doesn't pay the penalty sufficiently to fix it.

Re: The Tower Keeps Rising

#83

Post by ddp26 »

> I can ask an agent to add OAuth, you can ask one to add caching, and somebody else can ask one to rebuild the database from first principles and make the UI pink. Each change can be reasonable in isolation.

But this is just bad vibecoding? This would be bad if humans did it too. With agents or humans, you need to coordinate.

Re: The Tower Keeps Rising

#84

Post by VMG »

tekacs wrote: post #6

I've said for a long time that composability in software is a bit like playing Tetris: the lines have to clear. I feel like that gives an even more literal tower-rising metaphor, and that's what it feels like people using agents naively (and software engineers of lower skill or earlier-career), end up violating. Agents are getting better at folding things into themselves, especially if you direct them to... but unfor…

Isn't this just an effect of what the LLMs are RL'ed for? Solving short-horizon tasks.

I assume one can't benchmaxx multi-year long efforts, clean architecture, taste etc as easily as these "make tests pass" tasks

Re: The Tower Keeps Rising

#85

Post by zawaideh »

This is exactly what Marx meant by labourers being alienated from their work because none of them understood anymore how the repetitive task they did factored into the product sold.

We are going through a transition from a guild based software production with primitive division of labour to a machinery based one where AI is the steam engine and the job of the engineer is to build the production line, be the mechanic fixing the line, and also the assembly line worker.

Re: The Tower Keeps Rising

#86

Post by layer8 »

Gud wrote: post #37
tekacs wrote: post #6

I've said for a long time that composability in software is a bit like playing Tetris: the lines have to clear. I feel like that gives an even more literal tower-rising metaphor, and that's what it feels like people using agents naively (and software engineers of lower skill or earlier-career), end up violating. Agents are getting better at folding things into themselves, especially if you direct them to... but unfor…

Do you believe "micro services" can make a comeback? local daemons with an exposed API, each daemon vibe coded?

Microservices are about separate deployment. Regarding separating the development/maintenance of components, you can achieve that in a monolith by composing it out of corresponding modules/libraries with defined APIs. That’s good practice anyway.

Re: The Tower Keeps Rising

#87

Post by Tagbert »

cheschire wrote: post #82

Douglas Adams basically predicted Wikipedia on smartphones, and I suspect we are only a few years away from babelfish ear buds.

Apple AirPods and Google buds both can do automatic translation. It's still a little too slow and is a little clumsy to use but it's getting better fast.

Re: The Tower Keeps Rising

#88

Post by stavros »

maest wrote: post #63
stavros wrote: post #38

Earlier quoted context omitted.

Agreed, and ever since LLMs started being able to write competent code, I've noticed a massive difference in quality on codebases where I knew the technology, and ones I didn't. This is because I can much more efficiently steer the LLM on e.g. backend code, which is my expertise, vs yoloing everything on mobile, where I have no idea. The codebases using technologies I have no idea about tend to quickly become unmaint…

> two orders of magnitude more productive Shipping 100x more features per day?

Yes.

Re: The Tower Keeps Rising

#89

Post by conartist6 »

tekacs wrote: post #81
conartist6 wrote: post #20

Earlier quoted context omitted.

Why would it? It has optimized what it was built to optimize: this is the token-selling industry. Take note that the people hawking the dream of a gold rush are not actually mining but selling shovels

Labs are trying to make long-horizon work. Even if you're a coding agent, adding more and more surface area is distracting to that goal. There is reason that RL over long traces should, at least in principle, optimize for building in ways that help the result fit in the model's context window. A meaningful risk of course is that the tools available to the model (ripgrep + fancier semantic approaches) allow it to do a…

Does that not sound a little silly to you when you say it? Should I invest in becoming a memory athlete as a way of becoming a better software engineer? ...or should I learn how to build and use tools?
Post reply on HN