Coding with LLMs in the summer of 2025 – an update • Hacker News Board

Re: Coding with LLMs in the summer of 2025 – an update

#381

Post by darkoob12 » Mon, Jul 21, 2025, 1:13 PM UTC

Aurornis wrote: post #290

ozgung wrote: post #126

Earlier quoted context omitted.

> The excuse "but you earn six figures, what' $200/month to you?" doesn't really capture the issue here. Just like every other subscription model, including the one in the Black Mirror episode, Common People. The value is too good to be true for the price at the beginning. But you become their prisoner in the long run, with increasing prices and degrading quality.

I don’t get it. There are multiple providers. I cancel one provider and sign up for someone new in a few minutes when I feel like changing. I’ve been doing this every few months. I think the only people worried about lock-in or Black Mirror themes are the people who are thinking about these subscriptions in an abstract sense. It’s really easy to change providers. They’re all improving. Competition is intense.

In the early days of the Web, competition was intens in Search Engine market but eventually one of them won the competition and became the only viable option. I expect this will happen to AI as well. In future only one AI company will dominate the market and people will have no choice but to use it.

Re: Coding with LLMs in the summer of 2025 – an update

#382

Post by spaceman_2020 » Mon, Jul 21, 2025, 1:17 PM UTC

cratermoon wrote: post #67

airstrike wrote: post #46

I think all conversations about coding with LLMs, vibe coding, etc. need to note the domain and choice of programming language. IMHO those two variables are 10x (maybe 100x) more explanatory than any vibe coding setup one can concoct. Anyone who is befuddled by how the other person {loves, hates} using LLMs to code should ask what kind of problem they are working on and then try to tackle the same problem with AI to…

They should also share their prompts and discuss exactly how much effort went into checking the output and re-prompting to get the desired result. The post hints at how much work it takes for the human, "If you are able to describe problems in a clear way and, if you are able to accept the back and forth needed in order to work with LLMs ... you need to provide extensive information to the LLM: papers, big parts of t…

As someone who just used AI to create a very comprehensive creative visual marketing campaign, there is absolutely a massive gap in output depending on your prompting skills

You can get images that can go straight to print or end up with pure slop based on your prompt

Re: Coding with LLMs in the summer of 2025 – an update

#383

Post by smokel » Mon, Jul 21, 2025, 1:22 PM UTC

senko wrote: post #337

dbingham wrote: post #302

Earlier quoted context omitted.

The same, in theory, applies to social media. But they've all enshittified in very similar ways now that they've captured their audiences. In theory there is intense competition between Meta, Twitter, TikTok, etc, but in actuality the same market forces drive the same enshittification across all of those platforms. They have convergent interests. If they all force more ads and suggested posts on you, they all make mo…

> The same, in theory, applies to social media. It absolutely does not. Your use of social network derives value from your network. If you switch, you have to convince everyone else to switch as well. It's a tremendous barrier to switching. LLMs are for the most part interchangeable commodity.

Note that the comment you are replying to is speculating about the (not so distant) future. Be assured that companies will try their best to lock customers in.

One option is to add adverts to the generated output, and making the product cheaper than the competition. Another is to have all your cloud data preprocessed with LLMs in a non-portable way, so that changing will incur a huge cost.

Re: Coding with LLMs in the summer of 2025 – an update

#384

Post by smokel » Mon, Jul 21, 2025, 1:27 PM UTC

dakiol wrote: post #25

> Gemini 2.5 PRO | Claude Opus 4 Whether it's vibe coding, agentic coding, or copy pasting from the web interface to your editor, it's still sad to see the normalization of private (i.e., paid) LLM models. I like the progress that LLMs introduce and I see them as a powerful tool, but I cannot understand how programmers (whether complete nobodies or popular figures) dont mind adding a strong dependency on a third part…

> Programming used to be (and still is, to a large extent) an activity that can be done with open and free tools.

This was largely not the case before 2000, and may not be the case after, say 2030. It may well be that we are living in extraordinary times.

Before 2000 one had to buy expensive compilers and hardware to do serious programming. The rise of the commercial internet has made desktop computers cheaper, and the free software movement (again mostly by means of commercial companies enjoying the benefits) has made a lot of free software available.

However, we now have mostly smartphones, and serious security risks to deal with.

Re: Coding with LLMs in the summer of 2025 – an update

#385

Post by freeone3000 » Mon, Jul 21, 2025, 1:30 PM UTC

This is possibly the first HN AI article that actually matches my experience - where the models are good enough for small pieces other people have done once, or for where you might otherwise write a macro, but for anything beyond the scope of a single file write shitty code; and regardless, always have to be hand-held.

It’s a far cry away from “vibe code everything”, “this will eliminate jobs” that the current hype train is pushing, despite clearly using the agentic approach with large context provieee by Opus.

Re: Coding with LLMs in the summer of 2025 – an update

#386

Post by aitchnyu » Mon, Jul 21, 2025, 1:41 PM UTC

physicles wrote: post #85

dkdcio wrote: post #18

Earlier quoted context omitted.

this is a common pattern I see -- if your codebase is confusing for LLMs, it's probably confusing for people too

This fact is one of the most pleasant surprises I’ve had during this AI wave. Finally, a concrete reason to care about your docs and your code quality.

"What helps the human helps the AI" in https://blog.nilenso.com/blog/2025/05/29/ai-assisted-coding/

In future I'll go "In the name of our new darling bot, let us unit test and refactor this complicated thing".

Re: Coding with LLMs in the summer of 2025 – an update

#387

Post by michaelbuckbee » Mon, Jul 21, 2025, 1:46 PM UTC

dakiol wrote: post #25

> Gemini 2.5 PRO | Claude Opus 4 Whether it's vibe coding, agentic coding, or copy pasting from the web interface to your editor, it's still sad to see the normalization of private (i.e., paid) LLM models. I like the progress that LLMs introduce and I see them as a powerful tool, but I cannot understand how programmers (whether complete nobodies or popular figures) dont mind adding a strong dependency on a third part…

Genuine question as I don't understand the deeper aspects of this, but is it possible that we will see AI specific hardware in the future that will make local AI's more possible?

My general thinking is that we're using graphics processors which _work_ but aren't really designed for AI (lack of memory, etc.).

Re: Coding with LLMs in the summer of 2025 – an update

#388

Post by loudmax » Mon, Jul 21, 2025, 1:52 PM UTC

amelius wrote: post #376

KronisLV wrote: post #366

Earlier quoted context omitted.

The software is largely there: you can run Ollama, vLLM or whatever else you please today. The models are somewhat getting there: even the smaller ones like Qwen3-30B-A3B and Devstral-23B are okay for some use cases and can run decently fast. They’re not amazing, but better than much larger models a year or two ago. The hardware is absolutely not there: most development laptops will be too weak to run a bunch of tool…

Didn't Karpathy, in his latest talk, say something along the lines of: don't bother with less capable models, they are just a waste of time.

It probably depends what your objective is. One of the benefits you get from running less capable models is that it's easier to understand what their limitations are. The shortcomings of more powerful models are harder to see and understand, because the models themselves are so much more capable.

If you have no interest in the inner workings of LLMs and you just want the machine to spit out some end result while putting in minimal time and effort, then yes, absolutely don't waste your time with smaller, less capable models.

Re: Coding with LLMs in the summer of 2025 – an update

#389

Post by paulddraper » Mon, Jul 21, 2025, 1:58 PM UTC

asadotzler wrote: post #314

paulddraper wrote: post #254

Earlier quoted context omitted.

And you thought Visual Studio was free? Or Windows? Or an Apple Developer License? There are free/free-ish, options, but there have always been paid tools.

Paid tools were rarely monthly subscriptions without which you could not produce code or executables. Further, I can write and compile an application for Mac, Windows, or Linux with entirely free tools including tools provided directly by Apple and Microsoft. This discussion is about is a monthly subscription, without which, most up and coming coders, certainly "vibe coders," are completely dead in the water. These t…

You can write code with free tools.

Re: Coding with LLMs in the summer of 2025 – an update

#390

Post by rwallace » Mon, Jul 21, 2025, 2:06 PM UTC

darkoob12 wrote: post #381

Aurornis wrote: post #290

Earlier quoted context omitted.

I don’t get it. There are multiple providers. I cancel one provider and sign up for someone new in a few minutes when I feel like changing. I’ve been doing this every few months. I think the only people worried about lock-in or Black Mirror themes are the people who are thinking about these subscriptions in an abstract sense. It’s really easy to change providers. They’re all improving. Competition is intense.

In the early days of the Web, competition was intens in Search Engine market but eventually one of them won the competition and became the only viable option. I expect this will happen to AI as well. In future only one AI company will dominate the market and people will have no choice but to use it.

I'm seeing quite a few people on this site recently talking about their Kagi subscriptions, claiming it is sufficiently better than Google to be worth the money.