I really don't think that's how it works. Smart, experienced developers who thought coding agents were junk for most of 2025 and think they're useful now in 2026 are not saying that because they got "worn down over time".

As a smart, experienced developer who's getting worn down over time, I disagree.

I was getting useful coding work done with GPT 3.5. I think devs saying "the models are finally good enough" this year are just trying to save face from their own previous irrational denials.

Useful, yes, sometimes, but it wasn't fully automated "Here's our JIRA board URL, fix everything that's rated 1-3 story points and in the current sprint".

Now it is.

I didn’t start using Claude Code until late 2025. Prior to that I would use ChatGPT to give me snippets of code but I was still doing most of the actual code writing. Coworkers told me in late 2025 about how they hadn’t written a line of code in “months” and just use Claude Code/agentic “whatever” so I tried out Claude Code and was pleasantly surprised. It is passable to have entire apps written by LLMs (I’ve made several that I otherwise never would have had the time to create by hand), but I wouldn’t say maintainable or easily extendable. It’s hard to be specific, but there’s something about LLM code that doesn’t look “natural”, and I’m not talking about the excessive use of comments in code. The code itself is unnatural. Functional, but unnatural. I wouldn’t want to suddenly lose LLMs and have to read through and understand and continue enhancing a codebase created by an LLM.

For me it feels a lot like generated images or video. I've made lots of things now, but those that are 100% LLM written "work" but are uncanny, weird and the details are wrong everywhere you care to look in detail.

I think how I'd put it is like, it's a deterministic common denominator thing iterated on, but it's not really intuitive, it's not really "what makes sense" but rather "what would x look like", similar to how you point out it is when it comes to image generation

it's useful for scaffolding but after that I'm not sure how you could rely on it without being in the loop and directing how the code should be like

This has been my experience has well. For code generation, you have to really constrain these LLMs on your coding style, design goals, test cases, and overall expectations. I mainly use these tools to help my understanding of the code and to generate code for very specific problems. Even after all that setup and careful review I'd say it's still a net big speed up for certain software engineering tasks.

Jason Turner gave an excellent talk at last year's CppCon explain how he thinks tools can be used to make generative AI coding assistance safer and more productive. https://www.youtube.com/watch?v=xCuRUjxT5L8

It tends to be when the training data wanders into their area of expertise temporarily and they go “OMG, they hype is real. I was so wrong” and then a few releases later they’re on the train and furious that the skills in their domain space have not just stopped improving, but regressed. Cue someone else in a different part of the world starting the same cycle.

Meanwhile the guy who leaned in a year ago and gave up reading the output is beginning to see work grind to a halt and throwing more agents at it is increasingly not working.

You can see these tropes all over social media near constantly.

> You can see these tropes all over social media near constantly.

You should stop using social media as your yardstick.

> You should stop using social media as your yardstick.

Yes, don't believe people posting on HN.

What about terry tao?

Who?

But in all seriousness - you can even bring up Pope himself. Don't care. Show me data, show me the leaps our software made with all this 100x productivity boost. Show me a myriad of better LLVM projects, new usable kernels, and so on. Show me sharp decline in bugs and defects in existing projects.

Keep blog posts and HN comments.

Do you want a graph of exploits found vs time? Erdos problems solved vs time?

This is entirely my point. Observing reality, you can see how little impact any of this is truly having. Decision making, communication and alignment is not helped at all by LLMs, it’s just leaving developers with more laundry.

> Smart, experienced developers who thought coding agents were junk for most of 2025 and think they're useful now in 2026

The ones you make up in your brain don't count. I'm yet to see anyone serious reverse their claims.

Paul Ford wrote a great piece about this in the NY Times: https://www.nytimes.com/2026/02/18/opinion/ai-software.html?...

> November was, for me and many others in tech, a great surprise. Before, A.I. coding tools were often useful, but halting and clumsy. Now, the bot can run for a full hour and make whole, designed websites and apps that may be flawed, but credible. I spent an entire session of therapy talking about it.

Max Woolf is a good one: https://minimaxir.com/2026/02/ai-agent-coding/

> The real annoying thing about Opus 4.6/Codex 5.3 is that it’s impossible to publicly say “Opus 4.5 (and the models that came after it) are an order of magnitude better than coding LLMs released just months before it” without sounding like an AI hype booster clickbaiting, but it’s the counterintuitive truth to my personal frustration. [...] A year ago, I was one of those skeptics who was very suspicious of the agentic hype.

DHH - https://newsletter.pragmaticengineer.com/p/dhhs-new-way-of-w...

> Six months ago, in an episode of the Lex Fridman podcast, David shared how he doesn’t use AI tools to write code: he types out all his code. But things have changed a lot since then.

> In this episode, we discuss his approach to building software, how it’s changed in the last six months, and why he now takes an agent-first approach, and how he barely writes any code by hand.

Linus Torvalds, two weeks ago (though I don't have evidence that he was a skeptic before) https://lore.kernel.org/linux-media/CAHk-=wi4zC+Ze8e+p3tMv8T...

> There are other questions around AI (like what the economy of it will actually look like in the end), but "is it useful" is no longer one of those questions. Anybody who doubts that clearly hasn't actually used it.

Donald Knuth! https://www-cs-faculty.stanford.edu/~knuth/papers/claude-cyc...

> Shock! Shock! I learned yesterday that an open problem I'd been working on for several weeks had just been solved by Claude Opus 4.6 - Anthropic's hybrid reasoning model that had been released three weeks earlier! It seems that I'll have to revise my opinions about "generative AI" one of these days. What a joy it is to learn not only that my conjecture has a nice solution but also to celebrate this dramatic advance in automatic deduction and creative problem solving.

Okay so you have no names of experienced developers saying that coding agents are now useful when they weren't before. The only two you have actually saying that are... not working as software engineers.

I don't think you are arguing in good faith here.

Max Woolf and DHH are clearly experienced developers who continue to write code for money.

Linus too - 11 commits to the kernel today! https://github.com/torvalds/linux/commits?author=torvalds

Plus this very thread is full of experienced developers who are saying that "coding agents are now useful when they weren't before":

- ACS_Solver: https://news.ycombinator.com/item?id=49052570#49057367

- suzzer99: https://news.ycombinator.com/item?id=49052570#49060743

- IshKebab: https://news.ycombinator.com/item?id=49052570#49056074

- smrtinsert: https://news.ycombinator.com/item?id=49052570#49055294

- qarl2: https://news.ycombinator.com/item?id=49052570#49053318

A few bonuses:

Mitchell Hashimoto: https://mitchellh.com/writing/my-ai-adoption-journey

> While I was still a heavy AI skeptic [... through to ...] At this point I was firmly in the "no way I can go back" territory.

Steve Klabnik: https://steveklabnik.com/writing/getting-started-with-claude...

> 2025 was an interesting year in many ways. One way in which it was interesting for me is that I went from an AI hater to a pretty big user.

Nolan Lawson: https://nolanlawson.com/2026/01/24/ai-tribalism/

> 2025 was a weird year for me. If you had asked me exactly a year ago, I would have said I thought LLMs were amusing toys but inappropriate for real software development. [...] Today, I would say that about 90% of my code is authored by Claude Code.

> I don't think you are arguing in good faith here.

Funny coming from a guy using Linus saying "There's no doubt AI is useful today" and interpreting that as "Yeah last year AI coding agents were garbage but now they're really useful".

There's no denying AI is useful. I use AI, my project at work is all about using LLMs. They're even useful for coding, when I don't give a fuck about the quality of the output (which is almost never in a work scenario).

But to claim that there has been some magical shift late last year is simply laughable. Anyone working as a software engineer and claims that is either lying to themselves or simply bad.

Oh and don't try with the "you're not prompting it right".

OK, you won't except Linus. How about DHH, Max, Nolan, Steve, Mitchell, and those five HN commenters?

Or to strengthen the case for Linus, here he is on June 16th 2926 saying: https://youtu.be/YKkEe-PxW10?t=1687

> we certainly saw more junk being generated by LLMs than we saw useful code up until the like early this year

Man who cares what they are saying?

The world needs to SEE what is coming out of all this spending. Guess what? It aint much! Thats why firms are in a hurry to review their expenditures and switch to chinese offerings.

I hate to break it to you - but wake up. You are not living in reality.

> How about DHH, Max, Nolan, Steve, Mitchell

Oh yes, dev celebs that rely on constant validation through social media. Very reliable source of data.

What about Uncle Bob of clean code? This is a bit embarrassing for you.

Uncle Bob was a dev celeb before there were dev celebs.

So far you have ignored celebs/stalwarts and normal people as well. So it is quite convenient to draw boundary that exactly includes people like you

OK, now do ACS_Solver, suzzer99, IshKebab, smrtinsert, and qarl2.

You're being one of the voices trying to do the wearing down right now in this very thread imo

Of course it doesn't seem that way to you. Preachers view themselves as spreading the good word, they don't see how annoying it is being preached at