It's crazy realizing that Claude Code only started getting big in the last year or so. It feels so different now, with all the new models & tools we have to use. I hope you enjoy!
I guess, its debatable that o1 was the real start- but I think its hard to deny that Claude Code CLI was the first time we had what we now call a coding harness hit the mainstream. And- Sonnet 3.7 was kinda Anthropic's "o1 moment".
God. Opus 4.6 and 5.3-codex feel like ancient history.
On the CLI side Aider had a good CLI product and the only relevant benchmark back in the day.
I think I would rather shoot myself in the head
I walked into a paint store recently and there was some interesting music playing on the PA. It was some sort of spanish-language 80s new wave I'd never heard before. It had a nice groove. I asked the guy at the counter about it and was surprised to find out it was AI.
So... was it as good as great music? No. But it beat the hell out of muzak. And it was genuinely novel in a way that pop music isn't. I will sacrifice a lot of pride for novelty.
AI music is a complete waste of compute. It exists only to further enrich an already wealthy stakeholder, and we should all be ashamed to have ended up in a place where it even exists.
And I think it can be uniquely fun, because it allows for the very rare combination of truly off-beat ideas with excellent execution.
In real life, it very rarely happens that somebody will spend a lifetime learning, gather a band, and then record something extremely off-beat. Because there are risks to that. Destroying your image, having to find people that are on the same wavelength, having to justify the time and money it costs to record something weird and not marketable.
Sure, people make weird stuff once in a while, but very rarely, and generally it takes unique individuals that find some particular weird niche to work in, like Weird Al or Max Raabe. And even then they tend to pick something relatively tame and marketable and stick to that.
But AI can bypass all that, and that makes things interesting.
My jaw literally dropped. Do you really believe this?
I think you just don't spend much time around people who love music.
It makes sense that someone like you would like AI music, I guess. You are clueless.
Sure. It happens in every field. When you invest a lot into something, it becomes risky or unprofitable to do some things.
Tech often drives things in the opposite direction. As it gets easier/cheaper/faster to create something, doing something odd and risky becomes easier to justify because there's less invested into it and there's fewer people whose cooperation is needed.
I'm not saying nobody does anything risky traditionally of course. But there's barriers to it, which become lesser once tech trivializes a good part of the process.
> It makes sense that someone like you would like AI music, I guess. You are clueless.
I like music in general, and am fairly indifferent as to how the goose is cooked. I listen to almost everything. There's no reason to exclude AI music. If it sounds good, it's good.
> Sure, people make weird stuff once in a while, but very rarely, [...] and even then they tend to pick something relatively tame and marketable and stick to that.
> But AI can bypass all that, and that makes things interesting.
> Very few people genuinely "love music" in the way that you have in mind.
Those claims. They clearly come from a tech person’s surface level understanding of the music industry, which is a tiny fraction of all music and not representative of why people make it or what they enjoy. "Very few people genuinely love music" says it all. Have some self awareness. You're describing nothing but your own narrow perspective.
There are a finite number of musicians in the world. Most of them are working on music that either 1) appeals to them, specifically, or 2) appeals to enough of an audience that they can eek out a living. And chances are, if you're hearing it in public, you're getting #2.
I want music that appeals to me. My tastes are broad but not infinite, and I've already thoroughly plumbed the depths of my favorite genres - many of which are largely ignored by modern musicians (see #2 above). AI offers a way of getting new music for neglected or underdeveloped genres. Spanish language 80s new wave combined with reggae? Why not?
I listen to a lot of music across many disparate genres. I even play music (for fun). I have also enjoyed some AI generated music. It's not either/or, I can listen to both.
But as we’ve seen with AI writing and AI art, the novelty wears off quickly. It’s dazzling at first, but once you start to hear more and more of it and pay closer attention to the finer details, it becomes more evident how samey and blurry and soulless it all is.
Real niche music is out there, and it’ll be more interesting and rewarding to find (or even create!) than any AI music could be.
This doesn't contradict GP at all. Very few people genuinely "love music" in the way that you have in mind.
> Your comment just shows how young you are.
And often the weirdest artists are also the most prolific because they tend to like experimenting for experimenting's sake.
Most of the "top 40" consistently comes across the same way to me (and pretty much always has), so.
>it was genuinely novel
Look, I don't know the song so I can't say how novel it is, but to me, it completely misses the point if its made by a music generation model. The point of music is not to make a bunch of novel sounds. Music is a means by which a human can express themselves, the whole _point_ of art is human expression.
Bird's aren't making art when they sing, I still like listening to birds. Why can't the sounds AI make be in the same category.
Human expression with art can go both ways from producing and experiencing.
For my part, I mostly dislike AI music. But if there was to be some AI music that I didn't already dislike for its content, then I would dislike it specifically for being AI. Call me close-minded if you will. Some people don't really like music at all. In general, I love music.
I saw a live band last week (daft punk meets prince), they wrote a song about Ai and used an auto tuner for it
> And it was genuinely novel in a way that pop music isn't. I will sacrifice a lot of pride for novelty.
For one thing, "interesting" and "novel" are not particularly the point of art. An infinite TikTok feed of AI slop is in some sense infinitely interesting and novel.
But also, those concepts are subjective. Pop music has a ton of evolution and innovation if you break it down. Sure, not every hit is doing something clever, but plenty of them are. You might not find those features to be interesting but it takes ingenuity to stand out in an era where the barrier to entry is so low.
2. Call it slop
3. Claim victory
Controversial take: AI shows that people simply don't give a shit and just confirms that mass culture is a mistake and the death of everything that is good and sacred.
Controversial take: For ages, it's been clear that most people have never given a shit, it just took AI for most to realize it.
My experience has been that AI music mostly is that.
You're right, this sure was a controversial take.
Anyway, surely this dichotomy only matters if your only choices are "AI generated music" and "autotuned, quantized, mass-market-optimized slop that dominates contemporary pop "music"". However, there is a bunch of good music outside of the "pop music" zone, which isn't AI generated, so why not go with some of that instead? Nobody is forcing you to listen to pop music.
I don't know what to tell you, but me and my kid are having a blast writing ridiculous songs and plopping them with song descriptions and some of those make it to our drive playlists.
Note: same guy; just not anywhere near my account
You are making the argument that the type of activity does not matter as long it is 'spending time', but to say that is almost reductionist to say that that it understates how ridiculously unnuanced an opinion it is. You might as well tell me that the quality of food does not matter and generic burger should suffice.
But what if I want a burger that is custom to me and not a generic slop generated by a human to appeal to the widest possible audience[1]? What if I want something that was created just for me? Good grief? Why do I have to defend having fun and why on earth would you assume that one is mutually exclusive to the other?
Geez man. [1]https://genius.com/Bo-burnham-repeat-stuff-lyrics
And I agree that "less AI" edit passes reduce a lot of the hallmarks, but I think these models truly struggle with expressing complicated ideas. Have Opus been good at that for you?
I think people should find this sort of result surprising by default. Like, presumably you don't know why your output isn't as good, or you'd fix it. So doesn't that lack of understanding concern you?
Good question! It mostly doesn’t concern me. I believe these models have a huge “latent space,” so it’s not surprising to me that other people, with the right harnesses and prompts, can get them to produce more-valuable content.
I spent a lot of time calibrating how I use these models to produce valuable, good code, right?
But as I alluded with my question above, I haven’t seen a ton of evidence that these models have human-level argumentation in that latent space. If my assumption there is wrong, then yes, I’d have to reexamine my understanding of these models.
Ah, fair, there's opportunity cost to that. May as well prioritize what you actually care about, yeah. Personally I'm fine with skimming through the prose in the default style, at least as long as the LLM isn't getting stuck in its own invented jargon. It'd be different if I were publishing that output as project documentation, but I don't even really want to try that.
> I haven’t seen a ton of evidence that these models have human-level argumentation in that latent space.
Not sure what you mean by argumentation. I'd agree that they don't seem to have flashes of insight or make intuitive leaps in the same way. But they clearly can follow through the logical steps of reasoning very thoroughly, once they know what to reason about. For a technology that seemed to struggle with understanding negation a couple years back, it's seemingly miraculous.
As a side effect having to read the code at least once inevitably makes it way shorter and usually much better.
Guess what: because I said "both", Opus decided I was looking to pick out exactly two of the issues. If I hadn't read that reasoning log, I would've remained oblivious and thought there were only two it could find.
This is like writing `if (cond_x && cond_y) {}` and then blaming the compiler because it didn't realise that actually meant to write `if (cond_x || cond_y) {}`.
But I don't think their prompt as written would have limited the responses to two, unless there really were only two matching both conditionals. I've not seen an LLM misinterpret language that way before.
0. "find issues that are both critical and related to X"
...could be read as "issues that are X and are Y":
1. [valid, intended] find [all] issues that are[, at the same time,] 1) critical; and 2) related to X
...or as "issues, both of which issues are X and are Y":
2. [valid, your reading] find [an to-be-specified number of] issues that are, both [so I want two issues], possessing X and Y attributes.
In this specific case, does it matter if you get the raw reasoning vs a "slop summary"? I bet both would tell you that Opus locked into two issues no matter how bad the slop summary is.
That seems like a misinterpretation of English that I'd expect from a much less capable model. Like, a complete lack of understanding of grammar. To have that meaning, you would have to have put "both" before "issues" instead.
I'd be curious to learn how you're using them.
Dude you should buy tin. I can get you a banger box for $30k.
> I still believe I use AI fairly typically, but I’ve had a notable change in background. Last October, I was an engineer on Microsoft’s Windows AI team. I am now a research engineer at Salesforce AI Research.
Priest wears robes.
I guess it’s one of those nonsensical automatic rules.
> I am now a research engineer at Salesforce AI Research. I spend more time supporting scientists & building rapid prototypes, rather than working with a large team of engineers.
I appreciate the PoV of people with different challenges, but my full-time job is not about building rapid prototypes so the guidelines are worth a bit less to me.
LLMs still mess up a lot if you just let them loose and don't guide what they do.
We're in our own bubbles where a good part of HN population woke up to coding agents being good enough ~1 year ago, there's a group of folks that found out ~6 months before that, and then the people banging their heads on these a bit earlier than that. If you aren't using a coding agent everyday most people are just using these things to apply an instagram filter, or sort a grocery list. Muse is probably the closest thing to 'full automation' a lot of people are seeing for the first time.
Unfortunately I don't think the bubble that exists at the moment is on the promise of automating so much coding as trying to penetrate consumer use cases, which I think are still lacking and not reliable enough yet. As much as I use coding agents every day I still will not let a claw-like near a bank account or a credit card.
While trying to capture that bug, I (ironically) asked Gemini (but the Gemini-via-Google-search Gemini, since Gemini proper was an outage) for the package name of a screen recorder (gtkRecordMyDesktop); the command it returned referenced a non-existent package¹. I then found an alternative, and then hit a bug in that screen recording software that I had to then work around to get the video file there.
The site I uploaded the video to, Imgur, breaks completely — i.e., it cannot even so much as surface an error message — if your browser refuses to let it store god knows what on your disks. (So as it is, I have an extension that says "why yes, of course you can have storage, and essentially provides a black hole. But since it looks like a "success" to the Javascript, the JS doesn't crash!)
This isn't, to me, some one-off interaction. Every interaction with software these days feels like this, more and more. Just breakages everywhere that leaves me wondering if "coding is solved", where is all the bug free software?
(¹forcefully prompting the AI to actually query the package listing netted me a classic "You're absolutely right! The package name I referenced does not exist!")
My experience is the same as yours. Every single service I use. Apps, websites, doesn't matter what. Every single one seems just softly degraded. Like I can't trust that features work any more. I could report the bug, but what's the point? It's going to go to some Claude triage agent who is going to "fix" it by slopping up the app even more. Do people even use their own websites and apps any more? Apparently not - the same people declaring software solved are having their AI agents doing computer use and going on these websites for them!
Claude, please read the Bible for me. Tell me what I need to do to get into Heaven. Oh, can you dictate it to me? I'm managing an agent swarm.
Bleh.
I know, I know, we are shit and AIs are a godsend for small shitty companies that have at least one clever person that architect their way out of a paper bag. I’m sure all ya’ll highly competent, genius academics don’t need it and find it a hindrance but the devs in my bubble really, really need it. And there are a lot of those..
Just find it funny how vibes based it all is, capabilities, experiences, anti-ai and pro-ai.
That being said, I don't understand what you are referring to.
It exists, at least in terms of ROI. Some enterprises are able to do successful rollouts that allow them to significantly shrink workforce in certain departments without losing quality (no, I'm not talking about customer support).
But most of the software is indeed getting worse right now. The industry is still figuring out how to wield these new tools and what to build with them. Those that figure it out faster than others will make billions.
I've noted the same but even before llms so I can't draw a conclusion there. I find strange issues with software I cannot explain. Not only breakages or bugs but also a strange lack of core features and UI/UX that leaves me wondering "am I dumb?".
b) you confuse technical quality with product incentives
If you see this, company doesn’t care about product. And Google doesn’t care about quality for at least a decade now, all they care is a share price and speed of delivery.
My annoyance is more specific than "it breaks". I hate how all this software (especially "web apps") just assumes that it will have permission to do whatever it wants and never contemplates that the user might have something to say about it.
But don't worry. Coding is solved.
The comments to this article suggest that it's still disputed.
Personally, I think it's a bit of a silly phrase, because it implies an absolute, and all anyone needs to do to disprove it is to show that coding was not solved for problem X. That's still the case -- it's just that the set of X is rapidly shrinking.
I think it's more indicative to say how much you trust LLM code. A little over a year ago, I scrutinised every line carefully, and it was buggy as hell and I had to fix most generated code by hand. Now, models write clean code with fewer bugs (far fewer) than I would. A year ago, I was doing a lot of steering during planning; now, it's rare that I don't agree with the model's first proposed solution, and even if I don't, it's most likely to fix a minor change in understanding, not to propose a substantial architectural change as it was before.
The one thing I'm not sure about is how much this is due to better prompting on my part. I doubt that this contributes much, but I still suspect that continual usage does make you more aware of what works and what does not: how much detail to provide, how to describe a problem or change, how to propose solutions while still leaving other options open.
It's just that most skilled developers find it disgusting, because the AI spits out code that doesn't work the way it should, and it all turns into the routine of "threw in a prompt, waited, reviewed, repeated." — only those who were crappy programmers are happy about this.
And on top of that, these characters deny the fact that agents are evolving too, and meat proxies will soon be unnecessary — or maybe already are: https://x.com/tunahorse21/status/2117353858544660585
To "know" this, people would have to believe it from their personal experience.
Many people have standards and experiences that differ from yours. Yes, even if they use frontier models.
What does amuse me to no end, however, is how many craftsfolk in AI circles are loudly rejecting AI imagery and video in favor of humans. The only folks who seem fine with that are the grifters looking to slop out a bunch of adverts quickly for commercial gain rather than do actual art, or folks who want “art” but don’t want to pay a human to make it for them or learn the skills themselves. Both of those camps are viewed with disdain and loathing by both sides of the AI Boom/Doom arguments, so I’ll take whatever allies I can get on those fronts.
AI music…man, I live with artisans and musicians and we have a number of “artists” we suspect are AI but whose music is pretty solid. We’re waiting for the shoe to drop, but I’m trying to look at it as a kind of turbocharged Fruity Loops/Logic as opposed to a human replacement. I hope I’m right on that, but time will tell.
The game changer I think more doomers need to experience is agents. It sounds like a recipe for disaster (a bunch of models known to hallucinate and allowed to run roughshod over a computer unattended? What could go wrong?), and it often (hilariously) is for the scammers out there giving it full access to production and fucking off to hawk their latest Masterclass on X or LinkedIn, but that first time you give it a reasonably achievable prompt and come back to a halfway decent product you can review and refine into production in 15m or less?
Absolutely magical, doubly so when it’s just 27B Qwen via Hermes and not some souped up stack in a frontier lab costing you thousands a month in tokens. If I were to evangelize AI, that’s how I’d do it. Fuck subscriptions, fuck cloud compute, fuck frontier labs and token buckets and whatever slop Sundar/Scam/Dario/Elmo et al are hawking this week; run that locally, give it a reasonable prompt that solves a real problem, and show them the results.
Then do the right thing and go for a walk with the two hours of free time the AI just freed up for you. Don’t ask for permission to take back your time.
...
>In case you’re wondering, I’m subscribed to: > Claude Pro ($17/ mo) > GitHub Copilot Pro ($10/ mo)
Nothing wrong there at all, amirite?
Maybe AI scrapped basic arithmetic and now those numbers are totally fine
> My most successful work this year was hand-writing a tool, replacing ~4,000 lines of vibe-code with a few hundred. My system has proven more flexible, easier to test, and more generalizable than what it replaced.
> agents still need human taste and experience to produce good work.
Where do you think human taste and experience in software comes from?
> overstimulating & exhausting in a way that coding never was.
> for many of us, honing the code, finding the right design, seeing the parts mesh together — that was the meditative purpose we found in our jobs.
> That’s not the only time AI waylaid me. LLMs could not figure out how to annotate that model’s training data correctly. I spent days going back and forth with them
> LLMs are not yet good companions when brainstorming complicated things.
Why do we expect this to get better? The training data will degrade in quality if more people rely on LLMs so I'd expect models to eventually start getting worse even if they currently enjoy apparent improvements in output.
> Writing code is solved.
What a strange thing to say given all the above experiences, which I think we all share.
Why are we willing to give up so much in terms of purpose and understanding for perceived productivity gains?
This always reads like “writing english is solved” just because you collected snippets of famous works and have built a spell corrector.
Code is written to process data. The struggle was never to learn programming syntax (most grammar are only a few page long). The main struggle was that it’s hard to model a domain into an information system, identifying the components and their relationships, what is ingested, and what needs to be output.
Computers have integers and floats, but you need to implement units like distance, money, various counts,… The real world have words and sentences, but that needs encoding like ascii and unicode as well as the “string” concepts to make it work. Take HN, I’d bet that if you can model it in terms of data, writing code is not an issue.
For 85-90% of devs, yes this was the struggle. Creating and updating rows in a database from user input is all the “domain modeling” there is in most software. That’s what is solved by AI and it’s the majority of software dev.
The issue here is that you are learning the syntax at the same time you are learning foreign concepts, and the syntax is often confusing and counter intuitive
Learning the syntax separately is of no use because without a mental model you can't do anything with it
This is why children can easily learn enough programming to create games, because it’s a domain they can comprehend easily. Just like they can use english to write about their daily lives. It will be simple sure, but it will work.
So learning to code is fairly easy, you can easily create simple programs after a weekend. More complex programs will still use most of the same basic concepts as far as coding goes, but you will need to master more complex concepts, and that takes time. And such concepts are not about coding, they are about the nature of computing or the domain the software is created for.
This is why experienced devs only need a few days doing kata to get up to speed with a new programming language. It’s usually the same old, with slight differences. What was always needed was an understanding of computing and the ability to break down problems and create a solution that can be computed.
Coding to me is the same as drafting an engineering schematics, or writing a sheet music. It’s just a tool, not the end result.
Those who think the challenge is to overreach the limitations imposed by programming languages and types, etc, to do seemingly "magical" things. These are ones who would never understand why you might want higher-kinded types, the relative pros and cons of the functional vs imperative approaches, or even of type systems in general. They also tend to think the code written, in itself, is the valuable output of their work.
And then there are those who think the challenges is to model problem domain so well, using the language features, types and data structures, etc, that the solution (and further adjustments to it) becomes obvious and straightforward. They also tend to think the analysis and model that results is what is valuable.
Another way to see this difference: what impresses them? it is a hack that uses arcane knowledge to bypass software and hardware "limitation" or structures? Or is it code that is simple but still effective at solving complex problems in elegant ways, that may look simple but reflects a huge amount of knowledge, skill, and architectural intuition built up over many years?
I of course think that the second group are more effective and are doing proper programming, but many programmers and the general public think otherwise, or can't event tell the difference. I once worked with some colleagues could never see the light, despite a lot of support from me.
So here is the kicker, the dissonance in response to AI, I think, is kind of analogous to these two groups. The first groups likes that the AI will not stop them, but rather get them much quicker to their "magic", whereas the second group is more skeptical and sees many issues with AI not seeing the big picture and understanding deeper intent.
The struggle is not where to put a semicolon. The struggle is, how do I handle validation problem X with framework Y.
If anything, I do expect the casual non-tech users to be making the most adaptable software because they have what they want in their head. Although, part of what the dev does is figuring out the weeds, and only a part of users have the patience to sit through detail corrections. And the AI user has to verbalize their wants exactly too.
Even with basic pseudocode and very lenient logical rules, most people won’t bother to provide a a good definition of some process, as it’s quite unnatural to be that logical. Instead, it’s mostly just playing around. When you ask the one that is supposedly 10x-ing his productivity to explain his mental model of their own projects, it’s often a wishlist instead of a real understanding of what he has built.
Those are the people who are most likely to give a monolithic prompt and then spend a week telling the machine 'I don't care about encryption or file permissions, just make it work.' Not to mention that most people can barely verbalize the problems they have with devices they use for 8hrs a day, let alone form a full, self consistant, project idea and then put it in writing.
Imagine you could build a piece of furniture without actually needing to know how to cut wood, drive nails etc. Imagine you could do it in 3d without knowing how to actually handle wood, you just have an image you can iterate on without actually costing you anything but time.
I remember the first big app I wrote in high-school. I had to learn C++, learn Qt etc. I knew what I wanted but putting that into code when I didn't know any of the libraries / tools was a huge time investment. If I had LLMs I could've done the same thing it took me 6+ months in probably less than a month.
They may have a perfectly good shot at being smart, but I still don't buy the argument. The reason they struggle to become coders (assuming they tried at all), in my experience, is a lack of problem-solving and debugging skills. There is no real shortcut here. An "image" of the chair isn't enough; when the first iteration is wrong, you have to be able to explain why it's wrong.
With a sufficiently good LLM these people will skip the tedious part of programming that most of us had the motivation / patience to go through. All the folks saying that actually writing code wasn't the bottleneck have had a LOT of years to get to that point, years a lot of people aren't interested in going through.
I'm not saying lay people will be able to join mega projects and work at FAANG. I'm saying a sufficiently courageous lay person will be able to make an app to automate whatever tedious birocratic process their niche work hasn't seen a product yet.
The years was not spent on learning how to code. The years was spent on learning about what needed to be coded. And that would have spanned multiple domains. Even the most basic production level software have multiple concepts that need to be integrated. And for that, they need to be learned.
Using AI without the requisite knowledge is playing Russian roulette. It’s kinda wanting to log into a file, and not thinking about disk storage being finite, and rotating the log file gives you flexibility. That’s not related to coding, it’s just hard thinking about the problem and the constraints (or finding a good book or article).
Every few months that revolver has a few more empty chambers and even if it shoots them in the foot, it can bandage them quite nicely. Will a solo lay person with an agent build a high quality high reliability software business? Doubtful. Will they be able to make a tool that helps them and 10 other people or a personal website? probably.
Just take a quick look around to see how many daily tools and utilities are actually built by experts and industries. Yes, you can put a plank on top of two concrete blocks to make a bench, but many people don’t and prefer to have good bench made, even when it’s quite easy to DIY one.
So I don’t foresee lots of people trying to make custom tools, more so to keep a subscription active.
And yeah, without LLMs, writing code absolutely can be the bottleneck sometimes, if only for psychological reasons. I've definitely experienced something like "coder's block" before. An anti-flow state, if you will.
(But skydhash is also right. The "unknown unknowns" are a big deal and there's only so much an LLM can do about that, at least unless the user is actively aware of the general shape of that problem and trying to learn via the LLM and fill in those knowledge gaps.)
I see this as HN bubble. For many on here it wasn’t a struggle, but for most people I think it is. Hence the SWE salaries.
AI changes the dispositions and difficulties, but it still favors a narrow selection of people to do the (still) difficult task of software engineering with agents.
RL is not dependent on training data. The mathocalypse didn't happen because they found better training data somewhere.
There are reasons to suspect that OpenAI may have intentionally or unintentionally trained on chat logs from mathematicians--mathematicians who were actively using OpenAI to try to to solve the same problems themselves.[1] If those mathematicians were on the right track, and getting close to a solution, that could be classified as finding "better training data somewhere."
[1] https://cybernews.com/ai-news/openai-accused-stealing-anothe...
I agree it’s unlikely this happened by accident, or entered training data (though not impossible), but it could certainly be within the context agents were using when tackling problems.
We have no evidence either way, but they had all the data they would need to do this.
Secondly most the posts on HN are from individuals. It doesnt represent group dynamics and how group/institutional knowledge works. For example there might be a regulation on publishing data every quarter. On the surface it looks like compliance but in reality different internal groups will hide data, delay it, fudge it etc etc. LLMs train on public data. Only after they are allowed access internally do they discover group knowledge. We are far away from seeing that happening.
As someone who wrote code for 27 years in all sorts of languages, not necessarily impressive code, but got paid for it, made a career, and changed life for the better multiple times, I don't think coding was ever an important part of the journey! Maybe it's cognitive dissonance, as you wrote above, but I believe taste comes from exploration, from trial and error, from being willing to be open and change old ways if new ways can improve how things are done!
Similar to taste in food or even music! You might think certain foods taste bad, but until you taste them, you won't be certain! Sometimes your senses will be right and the food will taste horrible; other times, you'll be fairly surprised. Similar to music—it's my life hobby—you might think certain genres or artists are bad, but until you sit down, give them a shot, and hear what they have to say, you won't know for certain if your judgment is correct.
If you meant by your comment that you need to code a lot to acquire taste and experience in software, I respectfully disagree. You are not completely wrong, though, but putting emphasis on code, if that's what you were going for, is an overstatement of code's importance. For that particular case, similar to the analogies mentioned above, it's about exploration and trying different languages, paradigms, solutions, and stacks, and unfortunately, we as humans have finite time, so we can't be trying and exploring fast enough to form judgments!
What I genuinely love about LLMs is mostly their exploratory powers. I try new stuff that I always wanted to try with actual products and form opinions about the whole experience.
Anyways, as I finished writing this, I realized, as always, I might be wrong! You might be right, taste is highly subjective! And acquiring it is a very personal thing! So I don't think right or wrong are important here!
I actually found this to be one of their strong points. Depends on the person / thinking style / communication style, I guess.
If I'm prompting with phrases like "Any ideas?", it's because I'm exploring a domain where I know I don't know a lot, and where I expect that there is enough prior art to get a foothold.
Its not a direct analogy, but this seems to me as like saying "I already know maths and english, why do we still hire and pay teachers". Its a massive issue that just seems to be hand-waved away as "we'll figure it out later".
To compound on the problem as well, even those of us who do still write code by hand are actively discouraged from sharing it, knowing no human will ever read it and we'll never be credited for our work, it'll just go in the pockets of a few big AI companies. I suppose there will be some that take some pride in knowing their code is helping AI models advance, but thats a small pool of an already small pool, assuming most people decide to just use the AI to write the code for them. A minority of a minority.
I guess this is the chickens coming home to roost of this whole attitude towards growth now, fallout later
"Perceived productivity gain" is a baseless conclusion. At this point it's abundantly clear that the productivity gain is real and massive.
Where I see the incoherence is in that people see too much value in code review and optimizations.
I believe many of the optimizations are premature. If you did not spot the problem in your QA testing, chances are it was not that important in the first place.
If the architecture wasn't perfect, it is now extremely cheap to change it later, as you realize real deficiencies. The agent will do it for you in a matter of hours, and largely on its own.
You will have to budget a lot of QA effort for verifying the significant changes before going to production, but I don't think it's a deal breaker.
Oh? Where is it? Why am I not seeing it as a user if it's abundantly clear? In none of the software I've used frequently in the last year have I seen any of those “real and massive” improvements. Not saying they don't improve at all, but the rate hasn't increased since the advent of LLMs.
I'm still waiting for that shiny new era of software productivity to impact any actual users.
Don’t take this as directed at you because I don’t know your background, but I’m starting to wonder if many who called themselves engineers here that have similar takes to this ever knew how to actually program to begin with.
you also were doing another 2 or 3 tasks in parallel while implementing them - just like with AI
sure, dimitrios :)
Anyways my point wasn’t to try and make myself out to be some John Henry (I could have done without the snarky "congrats", apologies). It’s that drowned out in the noise of AI based development, we forget that there are amazing software engineers out there (I’m not placing myself in this category) that were incredibly productive in a short amount of time. Quite some time ago, I watched, in awe, a live stream of two prominent Go developers completely rewrite the HTTP package, for example. And this was over the course of a night.
We need a new metric to gauge AI usefulness other than “I built this thing quickly”
The pool of programmers today is many times larger and less trained and so correspondingly most of today's programmers simply aren't very good and are astounded by feats that were once basic learning tasks.
Oh, and specifically the food logging part: no, you didn't do that in a couple of hours years ago. Taking pictures of food and having estimates grounded in your personal "recipe" library was a major research project until vLLMs came out.
In the beginning I was using GPT-5.4 in April.
I can't speak to what other devs are building, and there's certainly no lack of people pushing out slop made in a weekend.
Companies and teams with code review are not adapting at the same speed.
I figure it will take a few additional months for the benefits to become more noticeable to end users.
As someone working on the frontier, so to say, I believe I have a better picture.
Both of those things have changed a lot, and I think a year from now you will definitely see changes (maybe not massive, but still).
QA testing can't find missed optimization opportunities unless the performance is absolutely abysmal. Even then, it can't distinguish abysmal performance due to missing easy optimization opportunities from abysmal performance that's going to require you to sacrifice functionality.
If an app performs well because it caches the result of a slow function, it's going to pass QA just fine. If optimizing that slow function would make it fast, you can drop the cache and have a simpler and more robust app — but QA can never tell you that.
Is having a simpler and more robust implementation worth the time to review, understand, and improve it? I'd put that at easily 5-10x the effort.
If in the future performance was found inadequate, you could still have the agent revisit the slow function.
That's what I mean with the optimization being premature.
After struggling with some more complex features even after many iterations, I started to doubt, and questioned whether I'm writing myself into a dead-end.
I did not. I still made progress and things worked out just fine. Then Fable and later GPT-5.6 Sol came out, boosting productivity and complexity of features I could implement successfully.
The effort only ever went down, and my app was released in the AppStore last week, at about ~500k LOC.
I understand why people might believe that using AI and not manually cleaning up suboptimal or overly defensive implementation would eventually result in an unmaintainable mess.
Based on my personal experience and 500+ hours put into my project, I can confidently say that this is not the case. Increased effort to maintain is negligible.
Does it work both ways? How hard should we fight premature optimizations that LLMs are introducing? Or the crazy amount useless tests?
If the test suite takes too long, it can easily be cleaned up later rather than spending extra time judging test cases in every new MR.
Maintenance of test cases has also become trivial, even with thousands of them. When the pipeline goes red on master I click the new chat button and run /check-pipeline, where I put some concise instructions, and the failure gets investigated and resolved in short order.
What I think you're saying is that opinions that LLMs produce are good enough and malleable, so why even have an opinion?
Which is debatable - oftentimes their opinions are not good enough, and not malleable at all.
We're all still learning how to distinguish those. But in order to learn this, you have to read and understand the code they produce. LLMs can migrate a codebase to Rust, but they still suggest walking to a car wash. Every day they make decisions that humans would be fired for.
LLMs are definitely not yet capable enough to blindly trust them, and there's a pretty good chance they never will be.
You are assuming that AI should be trained on speicific field to reason better but it actually doesnt need to.
That is both untrue, and should be something that occurs rarely.
Past Mid level, most dicussion in code review is centered around the conceptual level. Code is mostly use to highlight the point being made. I’ve never seen the need for someone to rewrite a patch proposed by another person. Add to it or correct misunderstandings, but never sweeping changes.
Big +1 to that.
6 used to be the max for me as well when I worked with Claude Code in terminal windows. Too little to hold on to and to discern the conversations. Just walls of text.
I can now go 20+ with fun because
1. I built a canvas for organizing the work spatially, so every feature has its place,
2. I condensed sessions to a WhatsApp style chat with detailed agent steps available but folded away by default, and
3. Each feature agent ends with a demo, usually a narrated video that I can watch and comment on by voice as it runs.
(My solution is available open source and free: obeya.si)
However, I'm still split. Because this could mean that we see a jump in code quality, due to bad coders getting someone better to code for them. But we could see a decrease in code quality, due to less people "caring".
This is very much not my experience.
There is still questions about if that jira ticket should have been written but from ticket to mergable PR it's better than me.
I can virtually guarantee the bar for code can go so much lower as we rapidly deskill programmers.
We actually have a fabulous opportunity to generate much higher quality code products with AI.
And even in your case, with the eager AI student -- AI code education is much better than reading docs and struggling with tools. Students can now focus on the important software topics.
I remember my intro C++ classes and how many students stumbled on pointless & transient tooling , that was completely orthogonal to their proper engineering skills.
Now students can focus on their area of expertise and produce the highest quality possible without any resource restrictions.
I’m probably the best coder in my org, which doesn’t really say much, but at least allows me to judge about the room temperature. It is solved. I don’t say that’s you, but the only people who say it isn’t “that good” are the same people who used to yak shave, rename and move things 10 times until it “feels right”.
Between Opus 5.5 + GPT-6.1 Sol reviewer, most issues and unhandled edge cases are caught during implementation.
Then you QA test and provide the feedback.
I guarantee that this is enough to produce not only a working product, but is well capable of building apps much better than what is out there, without ever looking at the code.
Depending on your product and risk tolerance you may disagree. I believe that for the vast majority of use cases the approach I described, combined with extensive manual testing, is entirely adequate.
It's worth noting that I also have a lot of guardrails and custom tooling around my own process to check code quality, QA functionality, limit blast radius of bugs, add observability, make deployments and rollbacks quick and low risk, etc.
If you want to provide a good, secure, user-empowering, performant product, you cannot delegate everything agents, I assure you. And, building your foundation on un-reviewed mess of code will come back to bite you (partly depending on how big you grow), the same way it does with humans, which management always think is not an issue until it becomes one.
Now, you don't have to take my word for. Think of this: why is every change to Claude Code making it worse now? It is not almost unusable for me after many regressions over past hew years in its UX. Is it because of a lack of AI being used in its development?
Because by my estimation we did build our products in such a way and have that experience, while you presumably did not.
As for Claude Code, they recently delivered a significant upgrade to the desktop app where some commented that it felt like they upgraded Opus 5.5 to 5.6.
It's in fact working great, and the days where it was buggy are in my view in the past.
As for the rest, I assure you that the product is much more performant, secure, and delivers far, far more value to my users than I ever could have done prior to AI-assisted coding. And I'm a staff level engineer with 25 years of coding experience across all kinds of organizations. I'm not the best coder, but I'm at least decent. AI has been a massive force multiplier for me, even as I agree that it's not perfect.
Unpacking a little more, I think the area you might be running into issues with is the idea that because I rarely open my IDE, I'm "delegating everything to agents". I'm really not. I review PRs (just not in my IDE), I steer higher-level abstractions in the broader system. To me, automated coding with a frontier model is definitely good enough that it's utterly pointless of me to read the internals of 99% of functions, even classes. Assuming the inputs are correct, the agents will get those details correct. And for the tiny fraction of the time when that's not the case, that's why we have adversarial review, guardrails, tests, o11y, quick rollbacks, etc, etc. Working at the level of how the broader building blocks of the system fit together, bisecting the software into low / medium / high risk areas so I can direct more of my scarcest resource (my attention) towards the highest ROI portions, and building the infrastructure (the "software factory") that the agents work within building and improving the product is where I can add the most value in November 2026.
Have you ever worked in a bigger tech company with tens of millions of lines of code and senior staff / principal engineers? In my experience, sure they're reading and writing code here and there, but that's not the value they provide. The value they provide is the broader architectural view of the systems and how they fit together. It's no different with AI.
We may differ in the level of review and steering we do a bit. I have worked in codebases approaching a 1 million LOC, and I am now working on a suite of products and libraries in a monorepo that would be the flagship products of my own small company.
I have defined a strong architecture, guardrails, and a way of working that the agents keep to. I approve almost every single edit they do in the terminal, but most of the time I do not have to read each line, because they are good enough. Every now and then, I catch them doing something egregious, and I correct or redirect them. Other times, they stop to ask me for direction. Still, I am faster and do more work with the help of the agents.
So, no I'm not saying the agents do not provide value; they help with a lot of grunt work, and they can write most code basically correctly. Where I am firmly still in the driver's seat is with architecture, UX, quality control, product invariants and standards, and the occasional tweak to lower level implementation details. These remain a lot of work, unless you are simply building CRUD forms.
This does not sound like "coding is solved". If coding is solved, then I can one-shot a complex software product into being, which is never going to be the case.
I'm not sure if this means we will see smaller and smaller firms as a sort of market darwinism rewards good AI use by solopreneurs, and as large organizations tear themselves apart, or if we see the way big firms hold people accountable for their work change dramatically.
I also wonder what happens to these solo-businesses as they need to hire their second employee. What goes from a personal workflow will need to become a business process. I bet a lot of solo operators will resist employee #2 at nearly every cost!
I think what people are missing is that people often become craftsman because we want to be able to keep the code adaptive and performant so we can provide business value quickly and efficiently.
The change is with models, the benefit dynamics of immaculately structured code changes dramitically. Now the real area you need to focus on is correctness and performance. Structure doesn't really matter unless it serves those two purposes, at least from the business value side.
As with eliminating other forms of abstraction, there's not much gain from doing so. Writing source code and then compiling it offers many useful checks, and greatly simplifies making changes. It's just something that may no longer be necessary at some point.
Nearly everyone I’ve worked with that would say this ended up being the in the bottom quartile of those shipping features and their code was often the most complex. At least in small, “fast”-moving companies.
A few people I have worked with have nailed it, but they were the ones to balance present and future weighted towards present.
Spec was good, all tests green, app worked. If I didn't actually go in and try to understand the code I would have shipped it like this.
So here is my question to people saying it's solved : do you actually know that it is or does it simply appear so because all the tests are green?
First of all, it sounds unlikely to me that such an implementation was made with Opus 5.5 while it never mentioned the workaround.
Secondly, if the performance was indeed inadequate, that's something I would have caught during QA testing and simply have had the agent fix it.
When I looked at a benchmark, it suggested Sonnet 5.5 wasn't much cheaper than Opus 5.5 at Low to Medium effort for similar performance. That might not be representative of real world use though.
Optimizing performance is one of the tasks best suited to AI, since the outcome is measurable.
I can't comment on complex algorithms specifically, but it's not at all the case that this works only for basic apps or cannot handle complex, performance critical work.
First, you question the model. I have reams and reams of conversations with Opus 5.5 that shows it makes architectural messes all the time
And then you are saying you needed to have performance tests (which many devs don't even bother with) to catch bad architecture?? lol
So what if the architectural problem is not one that would be caught with a performance test? It seems you lack imagination to think of all the ton of issues that that would be very complicated to catch with tests.
I don't think I commented on performance tests at all.
Maybe I lack imagination here, yes, but generally I go by experience rather than talking about imagined issues. That is precisely what many here seem to do when it comes to explaining why AI couldn't work for them, and why reviewing the code remains necessary.
Me: Why this:
> I'm adding a lookup to persistEphemeralVFolder so that a repeated search reuses the user's root vFolder with the same query instead of hitting the unique index.
Claude Opus 5.5: A search stores its query as an ephemeral root vFolder. The new unique index on (user, parent query, query) now rejects a second root vFolder with the same query. As written, persistEphemeralVFolder always inserts, so repeating a search would fail its insert, the retry with a fresh short code would fail too, and the search would return an error. The Ephemeral VFolder paragraph we rewrote in the SPECS also says a search reuses the existing vFolder with its query, so the user gets the same short code back.
The lookup I proposed would also copy the query-then-create logic already in the PUT /vfolders handler. A cleaner option is one shared engine function that finds or creates a vFolder by query, called by both the handler and persistEphemeralVFolder. Shall I do that, or keep the local lookup?
Churned for 6s · done 1:10 PM
Me: I mean, is it not cleaner to fix this: "persistEphemeralVFolder always insert"
And generally, we want the db and its indexes to do their work, not duplicating that in application code with pre-lookups and stuff
Claude Opus 5.5: You're right. Both persistEphemeralVFolder and the lookup I put in the PUT /vfolders handler should be replaced by a save with conflict keys (user, parent query, query), so the unique index decides whether a row is created or updated.
if the cost of writing code collapses, what are the barriers to including these kind of tests?
It seems like the flow and work when using LLMs has to change, spend longer on the plan, spend more time on defensive testing, have more comprehensive tests (input validation, cybersecurity, performance, data hygine) and less time on functionality
if you want to write code the old way where the architecture is human readable and the tests are an after thought, then thats on you if you then ignore the part where the human has to read it.
TLDR: either go full agent, or actually learn the code being produced, but not both.
… Yes? Of course recognizing the flaws in the code correlates with having high standards. That doesn't mean the flaws aren't there.
Product quality is an emergent property of high standards (aka code quality).
I envy you.
I believe that anyone who holds this position has been extremely lucky/fortunate to work with only top-tier developers. And does not read or work with open source projects.
Last year’s models are producing code better than _at least_ 50% of the developers I’ve worked with. Today’s frontier models are better than probably 75%. If the code that humans have been generating has been “good” (on average) or at least good enough, then the models that exist today are producing “good” code.
And the bar is already raised because every single one of those engineers now has access to the same models. So you need to be in the top 1% of the engineers armed with LLMs. You can't just rely on LLMs getting better. AI is not the great equalizer, it is, in fact the opposite.
Refactoring and clearing up tech debt is faster now than it's ever been, and assuming it'll be even better in the near future, why should anyone care about what is "good" right now?
(This is a devil's advocate kind of remark by the way, I'm very much in favor of good / quality code, but also realistic enough that nobody has or gets time to finetune code nearly as much as they should)
> my uncle can create software
Is considered great
> my uncle can create music or art
Is not considered great.
I guess humans have agreed, that art is a skill you must learn if you want to produce it, but engineering or software is not a skill worth learning and we are happy if computers can do that for us.
So it’s great and amazing if anyone can create their gizmos and software to help them but not if they create music or digital images, which apparently it is wrong to prompt, and not a sign of a great future.
If you specified to someone that the AI is replacing the farting-into-mic-core music genre, they would not care. Same with programming, the average person is not exposed to this
AI created art and photography keeps winning contests and people get all upset after the fact saying it's not real art. If it's not real art then why are the judges so impressed by it before they hear the word AI? I get the sentimental "but a soul that has experienced pain didn't create it" but if it's fun to look at and gives you joy is that not enough? And there is of course always a person in the loop creating it.
Definition of art: The conscious use of the imagination in the production of objects intended to be contemplated or appreciated as beautiful, as in the arrangement of forms, sounds, or words.
A director imagines the movie scene and has a rough storyboard sketched, then CGI artists make it who then usually have some form of algorithm or ML help them. I'm sure most people would agree that's art even though the director only had his thoughts interpreted by many different people / machines. Why is that so different than a person asking ChatGPT or Seedance to create something they (and only they) imagined? Is it the effort involved? What if they spent 2 hours refining 1 photo to obsessively to get exactly what was in their imagination onto the screen?
I guess this is what is missing from vibed AI art. Usually it's someone with a quick prompt and nothing else. No effort or creativity from the human and that's probably what we don't like about AI art.
This is different from AI art looking all the same though
I think AI art is much like ai coding where people used 1 model a couple of times then wrote it off completely as garbage. Then years of very quick progress happened and all the 10 fingers on a hand and every picture looking the same disappeared.
If you can make it through the first 20 images on civit and tell me nobody is expressing themselves or their imagination in some of these pictures I guess we agree to disagree.
If we are going to say, humans should learn these skills to produce this and not just keep typing prompts into a chatbot, I agree, but I also think it applies to maths, coding, engineering and everything else. I don’t see why we need to draw an arbitrary line around supposed art.
I'm a pretty big fan of this one and I'm not sure how anyone could say there's no creativity being shown just because it didn't take as much effort as it would've 5 years ago:
https://civitai.com/images/147579069
Being able to express your imagination with more fidelity should be celebrated shouldn't it? Taking what's in your mind and showing it to other people is a really neat thing that used to be restricted to a few people. Not sure why expanding it out is so controversial. And again once you take the word AI out of it you start to win a bunch of art contests, so it can't be all that bad.
Like I'm sorry that photo you sent me is dreadful, I find it hard to believe you chose it as an example of how ai "art" is good.
No; it's a conclusion about the product rather than the endeavour. People don't think of the software itself as "art", but as just a means to an end; so they don't mind the idea of any old fool being able to produce it.
Oddly enough, I've come to feel similarly about music. Most of what you hear in "pop music" is highly uninspired, including pre-AI; but it serves the purpose. And now we have AI that doesn't give any indication that it could compete with humans on mash-up ideas, experimental microtonal stuff, etc.; but executes "yet another four-on-the-floor, standard chord progression club anthem" very well. (Except the lyrics. Ugh.)
Oh and prefill is still a lot worse on local LLMs. Like 1-2 orders of magnitude worse.
Retroactively speaking, I engaged with the already agreed designs and used AI to find much better ways to do the same thing.
Overall, I wish people used AI even for System Design as that seems to have a higher impact.
...
> Last October, I was an engineer on Microsoft’s Windows AI team. I am now a research engineer at Salesforce AI Research.
That's generally not how "typical use" works.
Gen-AI can and is being used to make real, worthwhile movies. The best video model available, Seedance 2.5, can't produce clips longer than 30 seconds. The human artistry comes from which clips/shots you ask for and how you edit them together to tell a story. Plenty of people are doing good work here.
Here are some examples. Even if you don't like these personally, they aren't slop. You can feel the creator's intention behind them:
https://www.youtube.com/watch?v=2__VhU7_3lw
https://www.youtube.com/watch?v=gl3oob03rdE
https://higgsfield.ai/@nue_nue/projects/listen-to-meh
https://higgsfield.ai/@sssacccade/projects/hunger-ai-short-f...
(This one is mine, just FYI) https://www.youtube.com/watch?v=g8XUH2OXXfA
What struck me is that it's really close to photo realistic, but I would still have noticed it's AI by the tiniest continuity mistakes and visual cues, like slightly unnatural color grading and such. However, if I had seen this five years ago, I would have taken it to be a real recording with post processing that makes it look a bit polished, like Benjamin Button or Grand Budapest Hotel.
But still, if the thing is really bad it just makes my work harder so im trying to keep it stable, i am still reading the core of the system as much as i can, the agentic pipeline in this case. I have different reviewers working, custom company model, claude, codex they run in different stages of the projects like for SOLID, for linting, thats what we build the review agents for. I check the architecture and design documents throughly before starting, then the AI creates documents that the AI will consume and i check the details didnt changed, the same if you need example proof of concepts, like some inherited approach from the anchored spec driven times. At this point reading every line is not possible, not even worth it to discuss it at company level its not happening, so these kind of things are your safety net now so if anyone has other strats please do share them i think we all need them.
By keeping my manager, and their manager happy.
For whom thinks that there is no economic value in local AI stations beside privacy, availability, transparency, unresrtictibility etc...
I guess he hasn't seen CRAFT (1979) yet, which would not have been possible before AI.
Not that it redeems all the other AI thingies, it's always a mixed bag, yet I can't say a single bad thing about it.
That being said, I agree with this statement: "I believe they are the greatest teachers humanity has ever created." LLMs are exceedingly powerful at accelerating the learning process.
Anyone using a swarm of agents in November 2026 to write code is no longer at the frontier of capability.
Running multiple system prompts at once is a perfect example of anthropomorphism. We have this fantasy that a community of diversely aligned agents will somehow outperform a single well-aligned agent. There might be some cases where the random walk takes you where you want to go, but how stable and stressful do you want it to be?
Some of us are using AI as a means to make a living now. If I slip even a little bit on best practices my clients will likely turn into ghosts. Multi agent is an extremely expensive form of entertainment in this context. It's the entire basis for why we have these junkies trolling around HN complaining about how they can never get enough tokens. If I was still playing with these ideas in front of my customers I can guarantee I'd be 100% unemployed right now. They brought me in to make AI into a profit center, not a cost center.
Multiple studies have come out recently that AI use when not used as a tutor leads to loss of learning. It's a great way to ensure you end up jobless in the future when you forget even very basic syntax from no longer having to deal with hard problems. It's why pilots still fly manually by hand even though the autopilot can do practically everything.
Being charitable, perhaps they're mostly focused on efficiency, not overall capability. I can see that using swarms probably rarely results in solutions you couldn't reach with a single agent, at much higher cost. I think the tradeoff is that you get to the solution with less clock time though.
That said, the article text they quoted isn't even about swarms, it's just about the mental fatigue of juggling multiple single-agent threads. And there I agree with the article. I keep doing it because of agent speed, maybe I should just bite the bullet and get some $500 subs so I can use Astra ultrafast for everything. Only half joking...
Everything you said only applies to unleashing an agent swarm on a single feature. You are not wrong on your assessment there, but working on multiple features concurrently does come with its own challenges.
Me too! I've done several deep dives in various topics just in the last few weeks. I start off with some question I want answers to, and often end up with more questions along the way and I end up learning a ton.
For example I've been enthusiastic about nuclear energy for a long time and I've been wondering why don't we build more of it? It seems like such a great investment, the fuel is extremely cheap compared to the power it produces, even including disposal of waste and everything it seems to me like the best power source we have by far.
I've read things like "it's not economically viable" which I didn't really get - how can it both be cheap clean electricity and not economically viable? It turns out the problem is interest. If you spend $20B building a nuclear plant, you need to make enough money to pay the interest on that $20B. The plant itself will easily make much more than $20B over its lifetime but it won't cover the loan payments unless you can secure a contract with a customer willing to pay a very premium price for stable power for like 20 years.
On the other hand, China builds nuclear plants for like $3B which changes everything. They can do that because they've built lots of nuclear plants, so they have repeatable designs and established supply chains, experienced builders etc. We could do that too and I really think we should (we as in the rest of the world), I think we should invest in nuclear technology to build experience and supply chains etc in order to be able to make the technology economically viable for us. It seems to me that fusion will have exactly the same problem, if we ever even make it work. Good luck building "economically viable" fusion plants, they will certainly be a thousand times more complex than fission plants.
Anyway this wasn't supposed to be a comment about nuclear energy. I also did a deep dive on hydropower based on some claims I heard and learned lots of cool things about that. The LLM found lots of interesting source material for me, including a letter from our ministers of energy and finance talking about a proposed law change that might take effect next year which I would never normally read but since it basically answered many of the questions I had I ended up reading the whole thing and it was super interesting. It's also obviously a lot more credible than just the AI's claims.
Highly recommend trying it out about any topic you may be interested in. I use the free version of ChatGPT. I've also used the Google search AI a lot, I'll basically just Google a question and then proceed to ask followup questions etc.
I'm sure it's not all 100% correct but I'm also quite sure that most of it is pretty good quality, and it really helps when it includes links to sources, I often read the sources instead of the AI summary.
This is exactly the sort of investment governments are suited to make since they have access to extremely cheap debt. Or at least they did until recently, though still cheaper than private markets. China has access to debt with interest of only 1.6% which allows these projects to be very viable.
From the perspective of one company all you get is that one power plant that produces electricity so if that can't pay for itself you can't do it and that's the end of that story. From the perspective of a government you're also creating business opportunities elsewhere, there's a lot of economic activity that arises from these investments that is great for society at large, both on the supplier side in terms of companies delivering materials and components etc and downstream you're producing cheap electricity that can support anything from aluminium production to data centers and whatever else.
And most importantly, to me, it's clean. The only reason fossil fuels are economically competitive is because we're ignoring the future cost those emissions will incur.
If our predecessors played their cards differently, we could today be living in a world with abundant clean energy from nuclear and renewables. We could use this abundant energy to produce hydrogen from water, eliminating most emissions from transport as well - those that aren't already eliminated with EVs.
I have some hope that this vision can be realized, there seems to be movement towards it. Might end up being more about SMRs than large scale reactors though, which I think is a bit sad as SMRs seem to me like they compromise away some of the benefits of nuclear energy to solve the economic viability issue but I guess if they can make them work it's still a big step in the right direction.
LLMs are just a tool, you can one-shot a full project, but you still need an engineer to validate, it will catch some adjustments, then more tickets will be created from that and the cycle goes on and on.
Honestly this makes me skeptical of the whole piece. I get a pretty strong Gell-Mann amnesia effect from it[0]. It is not quite reliable enough that you can trust it, as when it is wrong it tends to be VERY wrong. In addition it is not like 99% accurate or something, but closer to like 80-90% or something.
[0]: The phenomenon of a person trusting newspapers for topics which that person is not knowledgeable about, despite recognizing the newspaper as being extremely inaccurate on certain topics which that person is knowledgeable about.
Does anyone find this to be true?
To me, this is a negative and mostly irresponsible use of AI.
OP dumped a huge PR (edit: not actually huge) on the Mumble maintainers,[0] which didn't match project conventions. He left a bunch of unresolved conversations with Claude that are hard to follow because it looks like an insane person having a conversation with themselves.
Then, the Mumble maintainers gave him pretty polite, patient feedback, and he just ignored it. No follow up for going on three months. Granted, the maintainers left the PR in the queue for four months, so it's not like OP is the slowest link, but I definitely wouldn't point to this as a win when there's basically no traction on the PR or any indication this will be merged.
[0] https://github.com/mumble-voip/mumble/pull/7180
Edit: radlad is correct that the PR is not "huge" at ~300 LOC. I was reading on my phone and didn't check the PR size and mistakenly trusted OP's assessment of "huge."
I do ensure these self-conversations are resolved so that the PR is clean when I ask other reviewers to have a look, and I don't think I'd do that on an open-source project. But I'm very much shrugging at this practice.
To me, there's two things you can mean with a PR:
- Open a normal PR: I personally attest to the quality of the code, and I'm ready for the maintainer to review/merge it.
- Open a draft PR: I have questions about proceeding and want to show you a work in progress to give context.
Any kind of intermediate work to prepare it for the maintainers should happen in a fork, not adding noise in the official repo. When you're done experimenting in the fork, then it can go to the main repo.
The maintainers clarified they'd prefer a single "all-in" commit, and OP hasn't (yet) addressed that.
Also, unless I'm misreading this PR, it's 270 lines added, 20 removed. I certainly wouldn't call that "huge."
This is not a huge PR under any software project in the world.