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

361–370 of 434 posts

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

#361

Post by MoreQARespect »

kossae wrote: post #261
overgard wrote: post #247

Earlier quoted context omitted.

I think it's an unlikely future. What I think is more likely is people will realize that every line of code written is, to an extent, a liability, and generating massive amounts of sloppy insecure poorly performing code is a massive liability. That's not to say that AI's will go away, obviously, but I think when the hype dies down and people get more accustomed to what these things can and can't do well we'll have a…

The point on investment is apt. Even if they achieve twice as much as they’re able to today (some doubts amongst experts here), when the VC funding dries up we’ve seen what happens. It’s time to pay the piper. The prices rise to Enterprise-plan amounts, and companies start making much more real ROI decisions on these tools past the hype bubble. Will be interesting to see how that angle plays out. I’m no denier nor bo…

The same thing happened with the first internet bubble. It didnt prevent the rise of the internet it just meant some players who, for instance, overinvested in infrastructure ended up taking an L while other players bought up their overbuilt assets for a song and capitalized upon it later.

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

#362

Post by dirkc »

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…

I've personally felt this way about many proprietary tech ecosystems in the past. Still do. I don't want to invest my energy to learn something if the carpet can be pulled from under my feet. And it does happen.

But that is my personal value judgement. And it doesn't mean other people will think the same. Luckily tech is a big space.

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

#363

Post by pcrh »

quantumHazer wrote: post #9

I'm going a little offtopic here, but I disagree with the OPs use of the term "PhD-level knowledge", although I have a huge amount of respect for antirez (beside that we are born in the same island). This phrasing can be misleading and points to a broader misunderstanding about the nature of doctoral studies, which it has been influenced by the marketing and hype discourse surrounding AI labs. The assertion that ther…

Quite. "PhD-level knowledge" is the introduction to one's PhD thesis. The point of doing a PhD is to extend knowledge beyond what is already known, i.e that which cannot be known by an LLM.

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

#364

Post by simonw »

otabdeveloper4 wrote: post #326
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.

a) Rent a GPU server. b) Learn to finetune your models. You're a programmer, right? Whatever happened to knowing your tools? OP is right, these people are posers and fakers, not programmers.

Have you had any success finetuning models? What did you do?

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

#365

Post by hhh »

viraptor wrote: post #267
ketzo wrote: post #263

Earlier quoted context omitted.

In what ways is that better for you than using eg Claude? Aren’t you then just “locked in” to having a cloud provider which offers those models cheaply?

Any provider can run Kimi (including yourself if you would get enough use out of it), but only one can run Claude.

Two can run Claude, AWS and Anthropic. Claude rollout on AWS is pretty good, but they do some weird stuff in estimating your quota usage thru your max_tokens parameter.

I trust AWS, but we also pay big bucks to them and have a reason to trust them.

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

#366

Post by KronisLV »

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…

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 tools, IDEs and local services alongside a LLM and will struggle to do everything at the pace of those cloud services.

Even if you seek compromise and get a pair of Nvidia L4 cards or something similar and put them on a server somewhere, the aforementioned Qwen3-30B-A3B will run at around 60 tokens/second for a single query but slow down as you throw a bunch of developers at it that all need chat and autocomplete. The smaller Devstral model will more than halve the performance at the starting point because it’s dense.

Tools like GitHub Copilot allow an Ollama connection pretty easily, Continue.dev also does but can be a bit buggy (their VS Code implementation is better than their JetBrains one), whereas the likes of RooCode only seem viable with cloud models cause they generate large system prompts and need more performance than you can squeeze out of somewhat modest hardware.

That said, with more MoE models and better training, things seem hopeful. Just look at the recent ERNIE-4.5 release, their model is a bit smaller than Qwen3 but has largely comparable benchmark results.

Those Intel Arc Pro B60 cards can’t come soon enough. Someone needs to at least provide a passable alternative to Nvidia, nothing more.

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

#367

Post by stingraycharles »

KronisLV wrote: post #366
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…

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…

And models like Qwen3 really don’t match the quality of Opus 4 and Gemini-Pro 2.5. And even if you manage to get your hands on 512GB of GPU RAM, it will be slow.

There’s simply so much going on under the hood at these LLM providers that are very hard to replicate locally.

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

#368

Post by LeafItAlone »

Fervicus wrote: post #218
LeafItAlone wrote: post #203

Earlier quoted context omitted.

You mean the same companies they are hosting their VCS in and providing the infrastructure they deploy their codebases to? All in support of their CRUD application that is in a space with 15 identical competitors? My codebase is not my secret sauce.

Sure, the codebase itself isn't special. But it's the principle and ethics of it all. These companies trained their models unethically without consequence, and now people are eating up their artificially inflated hype and are lining up to give them money and their data on a silver platter.

My opinion is that the value to be that I’ve been getting out of these tools in both my personal and professional projects is greater than value that they (and others using the downstream effects of them) get out of having my particular codebases.

Also, many of my personal projects are open sourced with pretty permissive licensing, so I’m not all that mad someone else has the code.

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

#369

Post by LeafItAlone »

jerrygenser wrote: post #208
LeafItAlone wrote: post #201

Earlier quoted context omitted.

>I am afraid that in a few years, that will no longer be possible (as in most programmers will be so tied to a paid LLM As of now, I’m seeing no lock-in for any LLM. With tools like Aider, Cursor, etc., you can swim on a whim. And with Aider, I do. That’s what I currently don’t get in terms of investment. Companies (in many instances, VCs) are spending billions of dollars and tomorrow someone else eats their lunch. T…

They can lock in by subsidizing the price of you use their tool, while making the default price larger for wrappers. This can draw people from the wrapper that can support multiple models to the specific CLI that supports the proprietary model.

At present, the tools are effectively the same. Claude Code, OpenAI Codex, Google Gemini, etc. are basically the same CLI tools. Every so often one will introduce a new feature (e.g. MCP support), but it’s not long before the others also include it. It is easy to swap between them (and Aider) and on tasks where I want a “second opinion”, I do.

Even if they make their tooling cheaper, that’s not going to lock me in. It has to be the best model or have some killer feature. Which, again, could be usurped the next day with the rate these tools are advancing.

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

#370

Post by LeafItAlone »

shivasaxena wrote: post #360
LeafItAlone wrote: post #196

Earlier quoted context omitted.

>The reason I don't like those arguments is that they merge two orthogonal stuff: Solving problems and optimizing your tooling. You can optimize PyCharm just as much you can fiddle with Vim's config. But you’re ignoring that the “optimizing tooling” is for the goal of making it easier for you. Its spending time now to decrease time spent in the long term. I spent over a decade with Emacs as my sole editor and have si…

If I may ask, why didn't you just use any available emacs config with python support? There are plenty on github, and ofc there's doom emacs, spacemacs, and probably others. I can tell you in my case it was because I did want to play with emacs and get my hands dirty. But that does shift the blame to me since it's hardly fair to blame emacs for being so extensible and fun.

I did. I’ve done that and tried them all (granted this was a decade+ ago where the landscape was probably different). But there were all lacking full IDE features like what PyCharm gave me.
Post reply on HN