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

271–280 of 434 posts

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

#271

Post by sneak »

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…

Strong dependency? I can still code without LLMs, just an order of magnitude slower.

There is no dependency at all.

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

#272

Post by jwpapi »

Thank you very much this is exactly my experience. I sometimes let it vibe code frontend features that area easy to test in an already typed code base (add a field to this form), but most of the time its my sparring partner to review my code and evaluate all options. While it often recommends bullox or has logical flaws it helps me to do the obvious thing and to not miss a solution! Sometimes we have fancy play syndrome and want to code the complicated thing because of a fundamental leak we have. LLMS done a great job of reducing those of my flaws.

But just because I’ve not been lazy…

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

#273

Post by ls-a »

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 on/for Apple has never been free. So it's not a surprise to some engineers. You're right that programming might become the way of Apple in the future. However, I think engineers should rejoice because AI is the best thing that happened to them.

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

#274

Post by vitaflo »

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…

Most people who develop software expect other people to pay for it. That's why devs make six figures. Yet devs want everything for free to create the software they charge money for? That's a bit hypocritical.

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

#275

Post by dcre »

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…

To be pedantic, I think it’s too late for a product with close to a billion monthly active users to be “normalized.”

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

#276

Post by bGl2YW5j »

nlh wrote: post #33

Can anyone recommend a workflow / tools that accomplishes a slightly more augmented version of antirez’ workflow & suggestions minus the copy-pasting? I am on board to agree that pure LLM + pure original full code as context is the best path at the moment, but I’d love to be able to use some shortcuts like quickly applying changes, checkpoints, etc. My persistent (and not unfounded?) worry is that all the major tools…

I use Jetbrains AI assistant for its great integration with the editor and the codebase, and have been experimenting with Claude Code too. Jetbrains Assistant still has better editor integration for things like reviewing generated diffs and generating code based on currently selected code.

My augmented workflow is to “chat” with GPT because it’s free and powerful, to refine my ideas and surface things I hadn’t thought about. Then I start writing code to get in to the flow of things. I’ve found if I use the LLM straight away, I disengage, become lazy and lose context and understanding over the code. In these situations, I’ve had to redo the code more often than not. Lack of understanding is one part of why, but more importantly, disengaged prompting leads to vague and incorrect outcomes.

When I’m very clear in my head about my goal, I create a prompt either directly from my cursor, or if the changes are larger, I ask the LLM to not apply the changes but instead show them to me. I do both these things within the IDE in the chat window. I review the code and sometimes I’m happy applying it as is, other times I copy and paste it and tweak it manually.

I’ve got barebones rules set up; I haven’t felt the need to go overboard. Jetbrains Assistant does a good job of passing relevant context to the model.

I keep my prompts top-down (https://en.wikipedia.org/wiki/BLUF_(communication)) and explicit. Sometimes I’m much more detailed than others, and I’ve found that extra detail isn’t always necessary for a good result.

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

#277

Post by firecall »

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…

A big issue will be if we see a further decline in SDK and API documentation.

Anecdotally, I recently find myself building a simple enough Android app for a client based on an iOS app I have already built.

I don’t really know Android dev, but know enough to get started having patched an App somewhat recently.

So started from scratch and having heard that the Android SDK had something similar to SwiftUI that’s what I went for.

In building the App I have found that Gemini is far more useful than Googles own documentation and tutorials.

The tutorials for basic things like NavBars is just wrong in places, maybe due to being outdated.

I’ve reported issues using the feedback tool. But still….

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

#278

Post by cadamsdotcom »

Having done a few months of this new “job” of agentic coding I strongly agree with everything in this post.

Frontier LLMs are easiest to work with for now. Open models _will_ catch up. We can be excited for that future.

You are able to learn things from LLMs, and you can ask them for recommendations for an approach to implement something. Or just tell your LLM the approach to take. Sometimes it overcomplicates things. You’ll develop an instinct for when that’s likely. You can head off the overcomplication ahead of time or ask for refactorings after the initial cut is built for you. After a while you get an instinct for which way will get the work done soonest. Most fascinating of all, it’ll all change again with the next round of frontier models.

You don’t need frontier models for every task. For instance I’ve been positively surprised by Github Copilot for straightforward features and fixes. When it’s obvious how to implement, and you won’t need to go back and forth to nail down finer design details, getting an initial PR from Copilot is a great starting place.

To everyone starting out, enjoy the ride, know that none of us know what we’re doing, and share what you learn along the way!

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

#279

Post by aseipp »

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.

Anthropic or Google offering a product and having margins they leverage is not "lock in" when there are dozens of alternatives at many various price points, including ones that can be run entirely locally (at high capex cost). It's like market fact #0 that, today, there is very little moat here other than capital, which is why OpenAI has now got multiple viable competitors despite their head start. Their APIs get copied, their tools get copied, the only way they remain competitive is with huge investments back into the core product to retain their leads. This is just what a competitive market looks like right now, and these offerings exist exactly because of downward pressure from other forces. The goal is of course to squeeze other players as much as possible, but these products have not yet proven to be sticky enough for their mere existence to do that. And there are many other players who have a lot of incentive to keep that downward pressure applied.

What you're describing is really just called "Offering a product for sale" and yes typically the people doing it will do, say, and offer things that encourage using their product over the competitors. That isn't "lock in" in any sense of the word. What are they supposed to do? Say "Our shit sucks and isn't price effective compared to others and we bring nothing to the table?" while giving you stuff for free?

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

#280

Post by andyferris »

bee_rider wrote: post #223
majormajor wrote: post #186

Earlier quoted context omitted.

I don't think it's subscriptions so much as consumer startup pricing strategies: Netflix/Hulu were "losing money on streaming"-level cheap. Uber was "losing money on rides"-level cheap. WeWork was "losing money on real-estate" level cheap. Until someone releases wildly profitable LLM company financials it's reasonable to expect prices to go up in the future. Course, advances in compute are much more reasonable to exp…

It isn’t even that unreasonable for the AI companies to not be profitable at the moment (they are probably betting they can decrease costs before they run out of money, and want to offer people something like what the final experience will be). But it’s totally bizarre that people are comparing the cost of running locally to the current investor-subsidized remote costs. Eventually, these things should get closer. Eve…

I think it’s the time slice problem.

Locally I need to pay for my GPU hardware 24x7. Some electricity but mostly going to be hardware cost at my scale (plus I have excess free energy to burn).

Remotely I probably use less than an hour of compute a day. And only workdays.

Combined with batching being computationally more efficient it’s hard to see anything other than local inference ALWAYS being 10x more expensive than data centre inference.

(Would hope and love to be proven wrong about this as it plays out - but that’s the way I see it now).

Post reply on HN