Discussion

Bram’s Thoughts

Rover222: Keep raging into the night, old guard.I think the vibe-coding-deniers have move of a cult vibe, personally.

operatingthetan: I think it is a 'cult' but also at the same time the inevitable future of engineering. The cult part are a subset of people who are not thinking about LLM code generation critically and blindly follow whatever trend is popular at this exact second.

saulpw: > That wouldn’t even be a big violation of the vibe coding concept. You’re reading the innards a little but you’re only giving high-level, conceptual, abstract ideas about how problems should be solved. The machine is doing the vast majority, if not literally all, of the actual writing.Claude Code is being produced at AI Level 7 (Human specced, bots coded), whereas the author is arguing that AI Level 6 (Bots coded, human understands somewhat) yields substantially better results. I happen to agree, but I'd like to call out that people have wildly different opinions on this; some people say that the max AI Level should be 5 (Bots coded, human understands completely), and of course some people think that you lose touch with the ground if you go above AI Level 2 (Human coded with minor assists).[0] https://visidata.org/ai

sbysb: > some people say that the max AI Level should be 5> of course some people think that you lose touch with the ground if you go above AI Level 2I really think that this framing sometimes causes a loss of granularity. As with most things in life, there is nuance in these approaches.I find that nowadays for my main project I where I am really leaning into the 'autonomous engineering' concept, AI Level 7 is perfect - as long as it is qualified through rigorous QA processes on the output (ie it is not important what the code does if the output looks correct). But even in this project that I am really leaning into the AI 'hands-off' methodology, there are a few areas that dip into Level 5 or 4 depending on how well AI does them (Frontend Design especially) or on the criticality of the feature (in my case E2EE).The most important thing is recognizing when you need to move 'up' or 'down' the scale and having an understanding of the system you are building

infinitewars: AI is just another layer of abstraction. I'm sure the assembly language folks were grumbling about functions as being too abstracted at one point

makerofthings: I totally see what you're saying, but to me this feels different. Compilation is a fairly mechanical and well understood process. The large language models aren't just compiling English to assembler via your chosen language, they try and guess what you want, they add extra bits you didn't ask for, they're doing some of your solution thinking for you. That feels like more than just abstraction to me.

seanosaur: I think it's still abstraction by definition, but you're right in that it's a much larger single leap than in the past.

bearjaws: This is nearly as dumb as the post that "Claude code is useless because your home built "Slack App" won't be globally distributed and won't scale beyond 50k users".As if 97% of web apps aren't just basic CRUD with some integration to another system if you are lucky.99% of companies won't even have 50k users.

semicolon_storm: It’s truly strange that people keep citing the quality of Claude code’s leaked source as if it’s proof vibe coding doesn’t work.If anything, it’s the exact opposite. It shows that you can build a crazy popular & successful product while violating all the traditional rules about “good” code.

tedd4u: Still, it's probably true that Claude Code (etc) will be more successful working on clean, well-structured code, just like human coders are. So short-term, maybe not such a big deal, but long-term I think it's still an unresolved issue.

operatingthetan: What I'm missing so far is how they produced such awful code with the same product I'm using, which definitely would have called out some of those issues.Perhaps the problem is getting multiple vibe-coders synced up when working on a large repo.

shimman: Yes that plus having tens of billions of gulf money certainly helps you subsidize your moronic failures with money that isn't yours while you continue, and fail to, achieve profitability in any time horizon within a single lifespan.

beart: AI is non-deterministic. Can it still be considered an abstraction over a deterministic layer?

reconnecting: > Then I explain what I think should be done and we’ll keep discussing it until I stop having more thoughts to give and the machine stops saying stupid things which need correcting.Users like the author must be the most valuable Claude asset, because AI itself isn't a product — people's feedback that shapes output is.

disposition2: > Users like the authorHe’s a pretty interesting fella, I imagine his work influenced a lot of people over the yearshttps://en.wikipedia.org/wiki/Bram_Cohen

hombre_fatal: Also, many of the complaints seem more like giddy joy than anything.The negative emotion regex, for example, is only used for a log/telemetry metric.I don't see how a vibe-coded app is much different from a fast-moving human-coded one.Especially since a human is still driving it, thus they will take the same shortcuts they did before: instead of a formal planning phase, they'll just yolo it with the agent. Instead of cleaning up technical debt, they want to fix specific issues that are easy to review, not touch 10 files to do a refactor that's hard to review.

rectang: > https://visidata.org/aiThanks for that list of levels, it's helpful to understand how these things are playing out and where I'm at in relation to other engineers utilizing LLM agents.I can say that I feel comfortable at approximately AI level 5, with occasional forays to AI level 6 when I completely understand the interface and can test it but don't fully understand the implementation. It's not really that different from working on a team, with the agent as a team member.

Schiendelman: I suspect a lot of it is just older, before Opus 4.5+ got good at calling out issues.

camdenreslink: I imagine it is way more affordable in terms of tokens to implement a feature in a well organized code base, rather than a hacky mess of a codebase that is the result of 30 band-aid fixes stacked on top of each other.

kypro: The argument against this is that human coders are also non-deterministic, so does it really matter if it's a human or an AI agent producing the code – assuming the AI agent is capable of producing human-quality code or better?I agree it's not a layer of abstraction in the traditional sense though. AI isn't an abstraction of existing code, it's a new way to produce code. It's an "abstraction layer" in the same way an IDE is is an abstraction layer.

bitwize: Value to customer. Literally the only thing that matters.

noosphr: I don't think anyone who used Claude code on the terminal had anything good to say about it. It was people using it through vs code that had a good time.

mwigdahl: I prefer using it via the terminal. Might be anchoring bias, but I have had issues with slash commands not registering and hooks not working in the plugin.

somewhatjustin: This reminds me of Clayton Christensen's theory of disruption.Disruption happens when firms are disincentivized to switch to the new thing or address the new customer because the current state of it is bad, the margins are low. Intel missed out on mobile because their existing business was so excellent and making phone chips seemed beneath them.The funny thing is that these firms are being completely rational. Why leave behind high margins and your excellent full-featured product for this half-working new paradigm?But then eventually, the new thing becomes good enough and overtakes the old one. Going back to the Intel example, they felt this acutely when Apple switched their desktops to ARM.For now, Claude Code works. It's already good enough. But unless we've plateaued on AI progress, it'll surpass hand crafted equivalents on most metrics.

tock: Huh what moronic failure did Anthropic do? Every Claude Code user I know loves it.

kennywinker: I think the thing is that people expect one of the largest companies in the world to have well written code.Claude’s source code is fine for a 1-5 person startup. It’s atrocious for a flagship product from a company valued over $380 BILLION.Like if that’s the best ai coding can do given infinite money? Yeah, the emperor has no clothes.

bcrosby95: Bad code works fine until it doesn't. In my experience, with humans, doing the right thing is worth it over doing the bad thing if your time horizon is a few months. Once you're in years, absolutely do the right thing, you're actually throwing time away if you don't. And I don't mean "big refactor", I mean at-change-time, when you think "this change feels like an icky hack."For LLMs, I don't really know. I only have a couple years experience at that.

Iulioh: Well, users or _paying_ users?It's an important distinction

jjk166: Probably either. And excluding non-paying users only further narrows the applicability.

NewsaHackO: The worst thing is that everyone but them knows how easy it is to take advantage of their blind hate. News companies, podcasts, and bloggers (such as this one) know they can just twist the thumbscrew and say "AI bad!" then rake in thousands of views/subs without even having to give a substantial argument.

andrenotgiant: > you can build a crazy popular & successful product while violating all the traditional rules about “good” codewhich has always been true

roncesvalles: It depends on the urgency. Not every product is urgent. CC arguable was very urgent; even a day of delay meant the competitors could come out with something slightly more appealing.

aleksandrm: Do we know if the original code was vibe coded? It's like chicken and an egg dilemma.

cube00: It's not a chicken and egg dilemma, the model can be used independently of Claude to write code, the heavy lifting is still done on their servers.

scrame: This is the guy that created bittorrent, btw. I know that was a long time ago, but he's not just some random blogger.

llm_nerd: Just like electing a reality show circus clown halfwit pedo to president probably isn't good advice, elevating some guy's opinion on AI tooling because he made a variation of a product he worked on in an employer for P2P piracy two+ decades ago isn't rational either.On the topic of AI his opinion should be treated as "random blogger".

scrame: and who are you?

llm_nerd: A "random blogger"? Hell, I don't even claim to be that. But the weird Cohen cultists who think his opinion is anything more than peanut gallery because of something he did two decades ago need to get a grip maybe.

acedTrex: Its a buggy pos though, "popular and successful" have never been indicators of quality in any sense.

ozgrakkurt: This is a really wrong perspective on software. Short term monkey style coding does not produce products. You might get money but that is not what it is about.This is similar to retarded builders in Turkey saying “wow, I can make the same building, sell for the same price, but spend way less” and then millions of people becoming victim when there is an earthquake.This is not how responsible people should think about things in society

matheusmoreira: Nobody rewards responsibility though. It's all about making number go up.

spoiler: Yes, and to add, in case it's not obvious: in my experience the maintenance, mental (and emotional costs, call me sensitive) cost of bad code compounds exponentially the more hacks you throw at it

babelfish: Sure, for humans. Not sure they'll be the primary readers of code going forward

thesz: This product rides a hype wave. This is why it is crazy popular and successful.The situation there is akin to Viaweb - Viaweb also rode hype wave and code situation was awful as well (see PG's stories about fixing bugs during customer's issue reproduction theater).What did Viaweb's buyer do? They rewrote thing in C++.If history rhymes, then buyer of Anthropic would do something close to "rewrite it in C++" to the current Claude Code implementation.

throwawayqqq11: Which proves, depending on competition and other context, you could "build" something successful with monkey on typewriters.

hintymad: It looks vibe coding, or at AI coding in general, has been challenging a few empirical laws:- Brooks' No Silver Bullet: no single technology or management technique will yield a 10-fold productivity improvement in software development within a decade. If we write a spec that details everything we want, we would write soemthing as specific as code. Currently people seem to believe that a lot of the fundamentals are well covered by existing code, so a vague lines of "build me XXX with YYY" can lead to amazing results because AI successfully transfers the world-class expertise of some engineers to generate for such prompt, so most of the complex turns to be accidental, and we only need much fewer engineers to handle essential complexities.- Kernighan's Law, which says debugging is twice as hard as writing the code in the first place. Now people are increasingly believing that AI can debug way faster than human (most likely because other smart people have done similar debugging already). And in the worst case, just ask AI to rewrite the code.- Dijkstra on the foolishness of programming in natural language. Something along the line of which a system described in natural language becomes exponentially harder to manage as its size increases, whereas a system described in formal symbols grows linearly in complexity relative to its rules. Similar to above, people start to believe otherwise.- Lehman’s Law, which states that as a system's complexity increases as it evolves, unless work is done to maintain or reduce it. Similar to above, people start to believe otherwise.- And remotely Coase's Law, which argues that firms exist because the transaction costs of using the open market are often higher than the costs of directing that same work internally through a hierarchy. People start to believe that the cost of managing and aligning agents is so low that one-person companies that handle large number of transactions will appear.Also, ultimately Jevons Paradox, as people worry that the advances in AI will strip out so much demand that the market will slash more jobs than it will generate. I think this is the ultimate worry of many software engineers.Intereting times.

tombert: I'm pretty sure that will be true with AI as well.No accounting for tastes, but part of makes code hard for me to reason about is when it has lots of combinatorial complexity, where the amount of states that can happen makes it difficult to know all the possible good and bad states that your program can be in. Combinatorial complexity is something that objectively can be expensive for any form of computer, be it a human brain or silicon. If the code is written in such a way that the number of correct and incorrect states are impossible to know, then the problem becomes undecidable.I do think there is code that is "objectively" difficult to work with.

azan_: > This is a really wrong perspective on software. Short term monkey style coding does not produce products. You might get money but that is not what it is about.Getting money is 100% what it is about and Claude Code is great product.

jaccola: It's also a context-specific scale. I work in computer vision. Building the surrounding app, UI, checkout flow, etcetera is easily Level 6/7(sorry...) on this scale.Building the rendering pipeline, algorithms, maths, I've turned off even level 2. It is just more of a distraction than it's worth for that deep state of focus.So I imagine at least some of the disconnect comes from the area people work in and it's novelty or complexity.

cyclopeanutopia: I've used and hate it, it's garbage.

AstroBen: 99.999999% of products can't get away with what Anthropic is able to - this is a one in a billion disruptive product with minimal competition, and its success so far is mostly due to Claude the model, not the agent harness

dogline: I think it's becoming clear we're not anywhere near AGI, we figured out how to vectorize our knowledge bases and replay it back. We have a vectorized knowledge base, not an AI.

mckn1ght: I like Tesler’s Theorem, which I recently heard about:> AI is whatever hasn’t been done yet

jmyeet: Capital. Owners. Hate. Labor.You are a cog, an unfortunately necessary (currently) cost that needs to be reduced because you're decreasing profits.This same thing has been a tension in Hollywood for many, many years. Studio execs hate creatives. They want to reduce everything they do to a formula that can be repeated en masse. It's why we get so many sequals and, most recently, so many reboots of existing properties. The real boon of streaming was that it allowed the studios to dismantle the residual system that kept people working in the industry.You, as a software engineer, are not special. Your leadership hates you because they need you and every dollar you cost is a dollar taken from profits. It doesn't matter that you produce more value than you cost. They will still actively suppress your wages whenever they can. They will collude with other companies to do it. In the 2000s there was the hiring cartel with Apple, Google, etc. Since the pandemic, it's the ever-present layoffs that only exist to suppress wages and get more unpaid labor. People who are in fear of losing their job aren't asking for raises.Vibe coding is just another effort to suppress engineering salaries. That's why it was created. That's why management likes it.Management would use you as fertilizer if there was an uptick in the stock if they could get away with it.

slopinthebag: Yes, just get hundreds of billions of dollars in investments to build a leading product, and then use your massive legal team to force the usage of your highly subsidised and marketed subscription plan through your vibe coded software. This is excellent evidence that code doesn't matter.

senordevnyc: I know this isn't your point, but Anthropic has raised about $70 billion, not "hundreds of billions".And they don't need a massive legal team to declare that you can't use their software subscription with other people's software.

CrzyLngPwd: I feel like vibe coding a product is functionally the same as prototyping.In the past, which is a different country, we would throw away the prototypes.Nowadays vibe coding just keeps adding to them.

Forgeties79: There’s a sample group issue here beyond the obvious limitations of your personal experience. If they didn’t love it, they likely left it for another LLM. If they have issues with LLM’s writ large, they’re going to dislike and avoid all of them regardless.In the current market, most people using one LLM are likely going to have a positive view of it. Very little is forcing you to stick with one you dislike aside from corporate mandates.

slopinthebag: Yes, you would expect a company paying millions in TC to the best software developers on the planet could produce a product that is best in class, and you would get code quality for free. Except it's regularly beaten in benchmarks and user validation by open source agents, some built by a single person (pi), with horrible code quality leading to all sorts of bad UX and buggy behaviour.Either they're massively overpaying some scrubs to underperform with the new paradigm, or they are squeezing every last drop out of vibe coding and this is the result.

layer8: I don’t know about moronic, but:https://github.com/ctoth/claude-failureshttps://github.com/anthropics/claude-code/issues/42796

freediddy: No, I completely disagree with this entire article.Bad code or good code is no longer relevant anymore. What matters is whether or not AI fulfills the contract as to how the application is supposed to work. If the code sucks, you just rerun the prompt again and the next iteration will be better. But better doesn't matter because humans aren't reading the code anymore. I haven't written a line of code since January and I've made very large scale improvements to the products I work on. I've even stopped looking at the code at all except a cursory look out of curiosity.Worrying about how the sausage is made is a waste of time because that's how far AI has changed the game. Code doesn't matter anymore. Whether or not code is spaghetti is irrelevant. Cutting and pasting the same code over and over again is irrelevant. If it fulfills the contract, that's all that matters. If there's a bug, you update the contract and rerun it.

il-b: Someone vibe-coded the brake control system in your car. It passes the tests. Is it good enough for you?

tokioyoyo: If you make a working and functional bad code, and put it on maintenance modeX it can keep churning for decades with no major issues.Everything depends on context. Most code written by humans is indeed, garbage.

nkohari: I don't disagree with your general premise that eventually it'll just be rewritten, but I have to push back on the idea that Anthropic will be acquired. Their most recent valuation was $380B, and even if they wanted to be acquired (which I doubt) essentially no company has the necessary capital.

thwarted: > It shows that you can build a crazy popular & successful product while violating all the traditional rules about “good” code.We already knew that. This is a matter of people who didn't know that or didn't want to acknowledge that thinking they now have proof that it doesn't matter for creating a crazy popular & successful product, as if it's a gotcha on those who advocate for good practices. When your goal is to create something successful that you can cash out, good practices and quality are/were never a concern. This is the basis for YAGNI, move-fast-and-break-things, and worse-is-better. We've know this since at least betamax-vs-VHS (although maybe the WiB VHS cultural knowledge is forgotten these days).

MBCook: VHS was not worse is better. It’s better is better.

kn0where: Specifically, VHS had both longer recording times and cheaper VCRs (due to Matsushita’s liberal licensing) than Betamax did. Beta only had slightly better picture quality if you were willing to sacrifice recording length per tape. Most Betamax users adopted the βII format which lowered picture quality to VHS levels in order to squeeze more recording time onto the tape. At that point Betamax’s only advantage was a slightly more compact cassette.Also to correct another common myth, porn was widely available on both formats and was not the cause of VHS’s success over Betamax.

toomuchtodo: Betamax was arguably better.https://en.wikipedia.org/wiki/Videotape_format_war

SoftTalker: Not in ways that the market cared about.

bluefirebrand: > The argument against this is that human coders are also non-deterministic, so does it really matter if it's a human or an AI agent producing the codeActually yes, because Humans can be held accountable for the code they produceHolding humans accountable for code that LLMs produce would be entirely unreasonableAnd no, shifting the full burden of responsibility to the human reviewing the LLM output is not reasonable either

sigbottle: am layman. is CV "solved" at this point, or is there more work to be done?

themafia: > And in the worst case, just ask AI to rewrite the code."And in the worst case just pay for it twice."That leads to a dead end.

nh23423fefe: your prediction is going to be wrong, even with all those caveats

mbreese: Arguably better quality, but at the cost of being shorter. In the great trade off of time, size, and quality, I think VHS chose a better combination.

is_true: There's also a business incentive for code produced by LLM companies to be hard to maintain. So you keep needing them in the future.

johnfn: "Laughing" at how bad the code in Claude Code is really seems to be missing the forest for the trees. Anthropic didn't set out to build a bunch of clean code when writing Claude Code. They set out to make a bunch of money, and given CC makes in the low billions of ARR, is growing rapidly, and is the clear market leader, it seems they succeeded. Given this, you would think you'd would want to approach the strategy that Anthropic used with curiosity. How can we learn from what they did?There's nothing wrong with saying that Claude Code is written shoddily. It definitely is. But I think it should come with the recognition that Anthropic achieved all of its goals despite this. That's pretty interesting, right? I'd love to be talking about that instead.

pron: 1. Vibe coding is a spectrum of just how much human supervision (and/or scaffolding in the form of human-written tests/specs) is involved.2. The problem with "bad code" has nothing to do with the short-term success of the product but with the ability to evolve it successfully over time. In other words, it's about long-term success, not short-term success.3. Perhaps most importantly, Claude Code is a fairly simple product at its core, and most of its value comes from the model, not from its own code (and the same is true on the cost side). Claude Code is relatively a low stakes product. This means that the problems caused by bad code matter less in this instance, and they're managed further by Claude Code not being at the extreme "vibey" end of the spectrum.

eloisant: The very definition of "vibe coding" is using AI to write software and not even look at the code it produces.

bs7280: In my opinion there are two main groups on the spectrum of "vibe coding". The non technical users that love it but don't understand software engineering enough to know what it takes to make a production grade product. The opposite are the AI haters that used chatgpt 3.5 and decided LLM code is garbage.Both of these camps are the loudest voices on the internet, but there is a quiet but extremely productive camp somewhere in the middle that has enough optimism, open mindedness along with years of experience as an engineer to push Claude Code to its limit.I read somewhere that the difference between vibe coding and "agentic engineering" is if you are able to know what the code does. Developing a complex website with claude code is not very different than managing a team of off shore developers in terms of risks.Unless you are writing software for medical devices, banking software, fighter jets, etc... you are doing a disservice to your career by actively avoiding using LLMs as a tool in developing software.I have used around $2500 in claude code credits (measured with `bunx ccusage` ) the last 6 months, and 95% of what was written is never going to run on someone else's computer, yet I have been able to get ridiculous value out of it.

il-b: > extremely productive camp somewhere in the middleHow do you quantify and measure this productivity gain?

gpt5: I don't know about direct measurements, but you definitely 'feel' it. Such as seeing that amazing visualization of Claude Code just a couple of days after the code was released. These things would not have been possible in the past.

forrestthewoods: Interesting breakdown of levels. I like it.I’m not sure I believe that Level 7 exists for most projects. It is utterly *impossible* for most non-trivial programs to have a spec that doesn’t not have deep, carnal knowledge of the implementation. It can not be done.For most interesting problems the spec HAS to include implementation details and architecture and critical data structures. At some point you’re still writing code, but in a different language, and it migtt hurt have actually been better to just write the damn struct declarations by hand and then let AI run with it.

saulpw: I agree, I'm venturing into Level 6 myself and it often feels like being one step too high on a ladder. Level 7 feels like just standing on the very top of the ladder, which is terrifying (to me anyway as an experienced software engineer).

edschofield: Any company worth more than Anthropic could (in principle) acquire them with a share swap.

datsci_est_2015: It’s also possible to sell chairs that are uncomfortable and food that tastes terrible. Yet somehow we still have carpenters and chefs; Herman Miller and The French Laundry.Some business models will require “good” code, and some won’t. That’s how it is right now as well. But pretending that all business models will no longer require “good” code is like pretending that Michelin should’ve retired its list after the microwave was invented.

tayo42: Those high end restaurants are more like art and exploration of food then something practical like code. The only similarity is maybe research in academia. There's not real industry uses of code that's like art.

datsci_est_2015: I used the extreme of the spectrum, I can’t imagine you’re arguing that food is binary good / bad? There’s a litany of food options and quality, matching different business models of convenience and experience.Research in academia seems less appropriate because that’s famously not really a business model, except maybe in the extractive sense

robbiewxyz: This is exactly true in my experience. The usefulness of AI varies wildly depending on the complexity, correctness-requirements, & especially novelty of the domain!This attribute plus a bit of human tribalism, social echo-chambering, & some motivated reasoning by people with a horse in the race, explains most of the disagreement I see in rhetoric around AI.

adrian_b: There is right now another HN thread where a lot of users hate Claude Code.To be fair, their complaints are about very recent changes that break their workflow, while previously they were quite content with it.

cladopa: "Ladran, Sancho, señal que cabalgamos"The ship has sailed. Vibe coding works. It will only work better in the future.I have been programming for decades now, I have managed teams of developers. Vibe coding is great, specially in the hands of experts that know what they are doing.Deal with it because it is not going to stop. In the near future it will be local and 100x faster.

anthk: "Aunque la mona se vista de seda mona se queda".A pig with lipstick it's still a pig.Or, aptly, as you quoted "Don Quixote":'Con la iglesia hemos topado'.(indeed Sancho), we just met the Church...

hollowcelery: There are a number of things that make code hard to reason about for humans, and combinatorial complexity is just one of them. Another one is, say, size of working memory, or having to navigate across a large number of files to understand a piece of logic. These two examples are not necessarily expensive for computers.I don't entirely disagree that there is code that's objectively difficult to work with, but I suspect that the Venn diagram of "code that's hard for humans" and "code that's hard for computers" has much less overlap than you're suggesting.

tombert: Certainly with current models I have found that the Venn diagram of "code that's hard for humans" and "code that's hard for computers" has actually been remarkably similar, I suspect because it's trained on a lot of terrible code on Github.I'm sure that these models will get better, and I agree that the overlap will be lower at that point, but I still think what I said will be true.

f-serif: Not AI but perfect example is Cloudflare. They have implemented public suffix list (to check if a domain is valid) 10 different times in 10 different ways. In one place, they have even embedded the list in frontend (pages custom domain). You report issues, they fix that one service, their own stuff isn't even aware that it exists in other places.

taurath: This isn’t the narrative, at least in any circle I speak to. The narrative is currently that everyone needs to strive to be using hundreds of dollars of tokens a day or you aren’t being effective enough. Executives are mulling getting rid of code review and tests. I’ve never seen such blind optimism and so little appreciation for how things can go wrong.

dheera: > It shows that you can build a crazy popular & successful product while violating all the traditional rules about “good” code.That was always the case. Landlords still want rent, the IRS still has figurative guns, so shipping shit code to please these folks will always win over code quality, unless the system can be changed.

chucklenorris: 1 is definitely false right now. I gave specs, tests, full datasets, reference code to translate to an llm and still produce garbage code/fall flat on it's face. I just spent one week translating a codebase from go to cpp and i had to throw the whole thing out because it put in some horrible bugs that it could not fix even burning 500$ worth of tokens and me babysitting it. As i said it had everything at it's disposal: tests, reference impl, lots of data to work with. I finally got my lazy ass to inplement it and lo and behold i did it in 2 days with no bugs (that i know of) and the code quality is miles better than that undigested vomit. The codebase was a protocol library for decoding network traffic that used a lot of bit twiddling, flow control, huffman table compression, mildly complicated stuff. So no - if you want working non-trivial code that you can rely on then definitely don't use a llm to do it. Use it for autocomplete, small bits of code but never let the damn thing do the thinking for you.

zozbot234: > Bad code or good code is no longer relevant anymore.It's extremely relevant inasmuch as garbage code pollutes the AI's context and misleads it into writing more crap. "How the sausage is made" still matters.

ahepp: What do you think about the argument that we are entering a world where code is so cheap to write, you can throw the old one away and build a new one after you've validated the business model, found a niche, whatever?I mean, it seems like that has always been true to an extent, but now it may be even more true? Once you know you're sitting on a lode of gold, it's a lot easier to know how much to invest in the mine.

tombert: I actually think that might actually be a good path forward.I hate self-promotion but I posted my opinions on this last night https://blog.tombert.com/Posts/Technical/2026/04-April/Stop-...The tl;dr of this is that I don't think that the code itself is what needs to be preserved, the prompt and chat is the actual important and useful thing here. At some point I think it makes more sense to fine tune the prompts to get increasingly more specific and just regenerate the the code based on that spec, and store that in Git.

alephnerd: This is actually a pretty good callout.Observability into how a foundation model generated product arrived to that state is significantly more important than the underlying codebase, as it's the prompt context that is the architecture.

sneak: Where is the evidence that people are obsessed with one-shotting and not doing the iterative back-and-forth, prompt-and-correct system he describes here? It feels like he is attacking a strawman.