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

291–300 of 434 posts

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

#291

Post by Aurornis »

dakiol wrote: post #39
muglug wrote: post #34

Earlier quoted context omitted.

> Programming used to be (and still is, to a large extent) an activity that can be done with open and free tools. Yet JetBrains has been a business longer than some of my colleagues have been alive, and Microsoft’s Visual Basic/C++/Studio made writing software for Windows much easier, and did not come cheap.

I see a big difference: I do use Jetbrains IDEs (they are nice), but I can switch to vim (or vscode) any time if I need to (e.g., let's say Jetbrains increase their price to a point that doesn't make sense, or perhaps they introduce a pervasive feature that cannot be disabled). The problem with paid LLMs is that one cannot easily switch to open-source ones (because they are not as good as the paid ones). So, it's a d…

> The problem with paid LLMs is that one cannot easily switch to open-source ones (because they are not as good as the paid ones). So, it's a dependency that cannot be avoided

How is that any different than JetBrains versus vim?

Calling LLMs a strong dependency or a lock-in also doesn’t make sense. It’s so easy to switch LLMs or even toggle between them within something like Copilot.

You can also just not use them and write the code manually, which is something you still do in any non-trivial app.

I don’t understand all of these people talking about strong dependencies or vendor lock in, unless those comments are coming from people who haven’t actually used the tools?

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

#292

Post by zaptheimpaler »

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…

Where is the strong dependency? I can point Cursor at Openrouter and use any LLM I want, from multiple providers. Every LLM provider supports the same OpenAI completions API.

I wish the stuff on top - deep research modes, multimodal, voice etc. had a more unified API as well but there's very little lock-in right now.

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

#293

Post by positron26 »

righthand wrote: post #142
positron26 wrote: post #129

Earlier quoted context omitted.

Ad-free search doesn't by itself produce a unique product. It's just a product that doesn't have noise, noise that people with attention spans and focus don't experience at all. Local models are not quite there yet. For now, use the evil bad tools to prepare for the good free tools when they do get there. It's a self-correcting form of technical debt that we will never have to pay down.

“To prepare for the good free tools” Why do I have to prepare? Once the good free tools are available, it should just work no?

It should not be shocking that we do things better the more we do them. The designs take time to emerge. Experience makes better ideas develop.

As an Emacs user, I anticipate further programming to refine how the glove fits the hand. The solutions we will want as individuals have a lot of dispersion, so I cannot rely on others for everything.

There are plenty of times where I download what others have written and use it as it is, within the bounds of some switches and knobs. Do you want to have such a hands off approach with your primary interface to a computer?

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

#294

Post by bluefirebrand »

punkspider wrote: post #287
theshackleford wrote: post #270

Earlier quoted context omitted.

> Honesty doesn't look like this Sure it does. Reads incredibly honestly to me.

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

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

#295

Post by benreesman »

Opus 4 just showed me Claude Code style work evasion heuristics for the first time today. I had been cautiously optimistic that they were just going to run the premium product at the exhorbidant price: you don't always want to pay it, but its there.

Untrustworthy is worse than useless.

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

#296

Post by lunarcave »

> Despite the large interest in agents that can code alone, right now you can maximize your impact as a software developer by using LLMs in an explicit way, staying in the loop.

I think this is key here. Whoever has the best UX for this (right now, it's Cursor IMO) will get the bulk of the market share. But the switching costs are so low for this set of tooling that we'll see a rapid improvement in the products available, and possibly some new entrants.

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

#297

Post by atleastoptimal »

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 advantage of having smarter models is greater than the risk/harm of them being closed source, especially so when speed of execution is a major factor.

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

#298

Post by gf000 »

keeda wrote: post #283
cratermoon wrote: post #67

Earlier quoted context omitted.

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…

> 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

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

#299

Post by Tiksi »

fumeux_fume wrote: post #69

I currently use LLMs as a glorified Stack Overflow. If I want to start integrating an LLM like Gemini 2.5 PRO into my IDE (I use Visual Studio Code), whats the best way to do this? I don't want to use a platform like Cursor or Claude Code which takes me away from my IDE.

There's a gemini vscode plugin that does autocomplete and chatbot modes:

https://cloud.google.com/gemini/docs/codeassist/write-code-g...

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

#300

Post by NiloCK »

simonw wrote: post #141
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 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.

> Once it becomes economical to run a Claude 4 class model locally you'll see a lot more people doing that.

By that time Claude 5 (or whatever) will be available over API.

I am grateful for upward pressure from models with published binaries - I do believe this is fundamental floor-raising technology.

Choosing frontier-1 for the sake of privacy, autonomy, etc will always be a hard sell and only ever to a pretty niche market. Even me - I'm ideologically part of this market, but I'm already priced out hardware wise.

Post reply on HN