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

Coding with LLMs in the summer of 2025 – an update

antirez.com

Post reply on HN
Print view View original

331–340 of 434 posts

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

#331

Post by dinkumthinkum »

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…

If you are so tied to an LLM that you cannot program without one then you are not a programmer. It is not the same as with an IDE or whatever, those are essentially ergonomic and do not speak to your actual competence. This will probably be an unpopular take but its just reality.

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

#332

Post by hyperadvanced »

1024core wrote: post #168

I have found that if I ask the LLM to first _describe_ to me what it wants to do without writing any code, then the subsequent code generated has much higher quality. I will ask for a detailed description of the things it wants to do, give it some feedback and after a couple of iterations, tell it to go ahead and implement it.

Seconded. Winsome strategy, plays to the strengths of the LLM without letting it run wild

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

#333

Post by YetAnotherNick »

> Coding activities should be performed mostly with:

> * Gemini 2.5 PRO > * Claude Opus 4

I think trying out all the LLMs for each task is highly underappreciated. There is no pareto optimal LLM for all skills. I give each prompt to 8 different LLMs using a Mac app. In my experience while Gemini is consistently in top 3 of 8, the difference between best output and Gemini Pro could be huge.

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

#334

Post by IshKebab »

gf000 wrote: post #298
keeda wrote: post #283

Earlier quoted context omitted.

> After all the effort getting to the point where the generated code is acceptable, one has to wonder, why not just write it yourself? Because it is still way, way, way faster and easier. You're absolutely right that the hard part is figuring out the solution. But the time spent typing is in no way trivial or cognitively simple, especially for more complex tasks. A single prompt can easily generate 5 - 10x the amount…

> frequently accounts for edge cases I hadn't considered, saving unquantifiable amounts of future debugging time; And creates new ones you wouldn't even consider before, creating just as much, if not more future debugging :D

Sure but you know about all the edge cases you know about, so you can fix bugs in those. The AI sometimes points out edge cases you didn't think of.

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

#335

Post by oblio »

QRY wrote: post #193
simonw wrote: post #141

Earlier quoted context omitted.

The models I can run locally aren't as good yet, and are way more expensive to operate. Once it becomes economical to run a Claude 4 class model locally you'll see a lot more people doing that. The closest you can get right now might be Kimi K2 on a pair of 512GB Mac Studios, at a cost of about $20,000.

Have you considered the Framework Desktop setup they mentioned in their announcement blog post[0]? Just marketing fluff, or is there any merit to it? > The top-end Ryzen AI Max+ 395 configuration with 128GB of memory starts at just $1999 USD. This is excellent for gaming, but it is a truly wild value proposition for AI workloads. Local AI inference has been heavily restricted to date by the limited memory capacity an…

One second, don't LLMs generally run in VRAM? If you put them in regular RAM, don't they have to go through the CPU which kills performance?

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

#336

Post by pxeger1 »

oblio wrote: post #335
QRY wrote: post #193

Earlier quoted context omitted.

Have you considered the Framework Desktop setup they mentioned in their announcement blog post[0]? Just marketing fluff, or is there any merit to it? > The top-end Ryzen AI Max+ 395 configuration with 128GB of memory starts at just $1999 USD. This is excellent for gaming, but it is a truly wild value proposition for AI workloads. Local AI inference has been heavily restricted to date by the limited memory capacity an…

One second, don't LLMs generally run in VRAM? If you put them in regular RAM, don't they have to go through the CPU which kills performance?

The mentioned CPU uses unified memory for its built in GPU / NPU. I.e. some portion of what could ordinarily be system RAM is given to the GPU instead of the CPU

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

#337

Post by senko »

dbingham wrote: post #302
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.

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.

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

#338

Post by oblio »

bluefirebrand wrote: post #294
punkspider wrote: post #287

Earlier quoted context omitted.

Seems both honest and rude, when it could've been honest and understanding. Responding to the original comment with 'get lost' and 'we don't want you either' is not constructive in my opinion.

I'm not sure why anyone expects this conversation to be constructive at this point People who are cheering for LLM coding because they hate actually coding themselves are cheering for programmers to lose their livelihoods I am not going to be polite and constructive to people who don't care if my livelihood is destroyed by their new tools. Why should I? They are cheering for my ruin

Or, you know, you could just... say nothing? Downvote and move on.

It's not like OP is Sam Altman and one of the actual AI bros. This thing will happen or not happen regardless of what OP wants.

Amusingly, you've committed the same basic mistake as LLMs, which just don't know when to shut up :-p

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

#339

Post by senko »

infecto wrote: post #284
jacobr1 wrote: post #206

Earlier quoted context omitted.

Our team has pretty aggressively started using LLMs for automated code review. It will look at our PRs and post comments. We can adding more material for different things for it to consider- from a looking at a summarized version of our API guidelines, general prompts like, "You are an expert software engineer and QA professional, review this PR and point out any bugs or other areas of technical risk. Make concise su…

I have been surprised more folks have no rolled these out as paid for products. I have been getting tons of use out of systems like cursors bugbot. The signal to noise is high and while it’s not always right it catches a lot of bugs I would have missed.

There are a few: Greptile, Ellipsis, GH Copilot (integrated with GH)

I feel many also try "review and fix automatically", as it's tempting to "just" pass the generated comments to a second agent to apply them.

But that opens a whole other can of worms and pretty soon you're just another code assistant service.

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

#340

Post by nominallyfree »

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…

Us FORTH and LISP hackers will be doing free range code forever.

We can use cheap hardware that can be fixed with soldering irons and oscilloscopes.

People said for decades our projects just become weird DSLs. And now whatever little thing I want to do in any mainstream language involves learning some weird library DSL.

And now people be needing 24h GPU farm access to handle code.

In 50 years my grandkids that wish to will be able to build, repair and program computers with a garage workbench and old wrinkled books. I know most of the software economy will end up in the hands of major corporations capable of paying through the nose for black box low code solutions.

Doesn't matter. Knowledge will set you free if you know where to look.

Post reply on HN