[HN Gopher] Coding after coders: The end of computer programming...
       ___________________________________________________________________
        
       Coding after coders: The end of computer programming as we know it?
        
       Author : angst
       Score  : 200 points
       Date   : 2026-03-12 10:29 UTC (2 days ago)
        
 (HTM) web link (www.nytimes.com)
 (TXT) w3m dump (www.nytimes.com)
        
       | bookofjoe wrote:
       | https://www.nytimes.com/2026/03/12/magazine/ai-coding-progra...
        
       | jazz9k wrote:
       | Because they are still making the same salary. In 5 years, when
       | their job is eliminated, and they can't find work, they will
       | regret their decision.
        
         | chrisra wrote:
         | Their decision to... use AI for coding?
        
           | lelanthran wrote:
           | Well, their position on AI.
           | 
           | By their own accounts they are just pressing enter.
        
         | siva7 wrote:
         | we had no choice. if i don't do it someone else will..
        
       | ripe wrote:
       | > it could also be that these software jobs won't pay as well as
       | in the past, because, of course, the jobs aren't as hard as they
       | used to be. Acquiring the skills isn't as challenging.
       | 
       | This sounds opposite to what the article said earlier: newbies
       | aren't able to get as much use out of these coding agents as the
       | more experienced programmers do.
        
         | kittikitti wrote:
         | This article is ragebaiting people and it's an embarrassing
         | piece from the NYT.
        
           | 0xcafefood wrote:
           | NYT has it out for digital advertisers, who directly compete
           | with them. I do sense some schadenfreude here that the tech
           | nerds who work at these places might be in trouble.
           | 
           | "Silicon Valley panjandrums spent the 2010s lecturing
           | American workers in dying industries that they needed to
           | "learn to code."
           | 
           | To copywriters at the NYT, LLMs are far better at stringing
           | together natural language prose than large amounts of valid
           | software. Get ready to supervise LLMs all day if you're not
           | already.
        
             | logicchains wrote:
             | LLMs are much better at coding now than at writing prose
             | that doesn't sound like slop.
        
               | 0xcafefood wrote:
               | The code is also recognizable as slop to those who know
               | how. Not the tropey "Not X, but Y" kind that's super easy
               | to spot. But tons of repetition, deeply nested code, etc.
               | 
               | A counterpoint is that (maybe) nobody cares if the code
               | is understandable, clean and maintainable. But NYT is
               | explicitly in the business of selling ads surrounded by
               | cheap copy just good enough to attract eyeballs. I
               | suspect getting LLMs to write that is going to be far
               | easier than getting LLMs to maintain large code bases
               | autonomously.
        
               | logicchains wrote:
               | >But tons of repetition, deeply nested code, etc.
               | 
               | If you explicitly make it go over the code file by file
               | to clean up, fix duplication and refactor, it'll look
               | much better, while no amount of "fix this slop" prompting
               | can fix AI prose.
        
               | 0xcafefood wrote:
               | > no amount of "fix this slop" prompting can fix AI prose
               | 
               | What's the proof for that? What fundamental limitation of
               | these large language models makes them unable to produce
               | natural language? A lot of people see the high likelihood
               | of ever increasing amounts of generated, no-effort
               | content on the web as a real threat. You're saying that's
               | impossible.
        
               | logicchains wrote:
               | >What fundamental limitation of these large language
               | models makes them unable to produce natural language?
               | 
               | LLMs can get indefinitely good at coding problems by
               | training in a reinforcement learning loop on randomly
               | generated coding problems with compiler/unit tests to
               | verify correctness. On the other hand, there's no way to
               | automatically generate a "human thinks this looks like
               | slop" signal; it fundamentally requires human time,
               | severely limiting throughput compared to fully
               | automatable training signals.
        
       | ramesh31 wrote:
       | Because we love tech? I'm absolutely terrified about the future
       | of employment in this field, but I wouldn't give up this insane
       | leap of science fiction technology for anything.
        
         | bigstrat2003 wrote:
         | I love tech - tech that actually works well. The current tech
         | we have for AI does not, so I'm not excited about it.
        
         | kittikitti wrote:
         | "One such test for Python code, called a pytest"
         | 
         | The brain rot from the author couldn't even think of "unit
         | test".
        
           | mkehrt wrote:
           | Why would you expect a reporter to magically know what a
           | "unit test" is? Sounds like a simple miscommunication with
           | one of his sources. Not perfect but not "brain rot".
        
         | hn_acc1 wrote:
         | A really good pattern-matching engine is an "insane leap of
         | science fiction"? It saves me a bit of typing here and there
         | with some good pattern matching. Trying to get it to do
         | anything more than a few lines gives me gibberish, or an
         | infinite loop of "Oh, you're right, I need to do X, not Y",
         | over and over - and that's Opus 4.5 or whatever the recent one
         | is.
         | 
         | Would you give it access to your bank account, your 401k, trust
         | it to sell your house, etc? I sure wouldn't.
        
           | ramesh31 wrote:
           | >A really good pattern-matching engine is an "insane leap of
           | science fiction"?
           | 
           | Yes, literally. The ship computer voice interface in Star
           | Trek was complete science fiction until 2022. Now its ability
           | to understand speech and respond seem quaint in comparison to
           | current AI.
        
       | deflator wrote:
       | What is a coder? Someone who is handed the full specs and sits
       | down and just types code? I have never met such a person. The
       | most annoying part of SWE is everyone who isn't an SWE has inane
       | ideas about what we do.
        
         | theshackleford wrote:
         | > The most annoying part of SWE is everyone who isn't an SWE
         | has inane ideas about what we do.
         | 
         | I've tended to hold the same opinion of what the average SWE
         | thinks everyone else does.
        
         | pjmlp wrote:
         | Never worked on offshoring projects? That is exactly what the
         | sweatshop coders do.
        
           | recursivedoubts wrote:
           | I think that the current AI tooling is a much bigger threat
           | to offshore sweatshops than to domestic programmers.
           | 
           | Why deal with language barriers, time shifts, etc. when a
           | small team of good developers can be so much more productive,
           | allegedly?
        
             | pjmlp wrote:
             | It certainly is,
             | 
             | https://www.theregister.com/2026/01/19/hcl_infosys_tcs_wipr
             | o...
        
           | Tade0 wrote:
           | No we don't.
           | 
           | For one, I never saw a "full spec" (if such a thing even
           | exists) back in my days of making 8k. Annually.
        
       | neonate wrote:
       | Other gift link: https://www.nytimes.com/2026/03/12/magazine/ai-
       | coding-progra...
        
       | zjp wrote:
       | There is no such thing as "after coders":
       | https://zjpea.substack.com/p/embarrassingly-solved-problems
       | 
       | This excerpt:
       | 
       | >A.I. had become so good at writing code that Ebert, initially
       | cautious, began letting it do more and more. Now Claude Code does
       | the bulk of it.
       | 
       | is a little overstated. I think the brownfield section has things
       | exactly backwards. Claude Code benefits enormously from large,
       | established codebases, and it's basically free riding on the
       | years of human work that went into those codebases. I prodded
       | Claude to add SNFG depictions to the molecular modeling program I
       | work on. It couldn't have come up with the whole program on its
       | own and if I tried it would produce a different, maybe worse
       | architecture than our atomic library, and then its design choices
       | for molecules might constrain its ability to solve the problem as
       | elegantly as it did. Even then, it needed a coworker to tell me
       | that it had used the incorrect data structure and needed to
       | switch to something that could, when selected, stand in for the
       | atoms it represented.
       | 
       | Also this:
       | 
       | >But A.I.-generated code? If it passes its tests and works, it's
       | worth as much as what humans get paid $200,000 or more a year to
       | compose.
       | 
       | Isn't really true. It's the free-riding problem again. The thing
       | about an ESP is that the LLM has the advantage of either a blank
       | canvas (if you're using one to vibe code a startup), or at least
       | the fact that several possibilities converge on one output, but,
       | genuinely, not all of those realities include good coding
       | architecture. Models can make mistakes, and without a human in
       | the loop those mistakes can render a codebase unmaintainable.
       | It's a balance. That's why I don't let Claude stamp himself to my
       | commits even if he assisted or even did all the work. Who cares
       | if Claude wrote it? I'm the one taking responsibility for it. The
       | article presents Greenfield as good for a startup, and it might
       | be, but only for the early, fast, funding rounds, when you have
       | to get an MVP out right now. That's an unstable foundation they
       | will have to go back and fix for regulatory or maintenance
       | reasons, and I think that's the better understanding of the
       | situation than framing Aayush's experience as a user error.
       | 
       | Even so, "weirdly jazzed about their new powers" is an
       | understatement. Every team including ours has decades of
       | programmer-years of tasks in the backlog, what's not to love
       | about something you can set to pet peeves for free and then see
       | if the reality matches the ideal? git reset --hard if you don't
       | like what it does, and if you do all the better. The Cuisy thing
       | with the script for the printer is a perfect application of LLMs,
       | a one-off that doesn't have to be maintained.
       | 
       | Also, the whole framing is weirdly self limiting. The
       | architectural taste that LLMs are, again, free riding off of, is
       | hard won by doing the work more senior engineers are giving to
       | LLMs instead of juniors. We're setting ourselves up for a serious
       | coordinated action problem as a profession. The article gestures
       | at this a couple times
       | 
       | The thing about threatening LLMs is pretty funny too but
       | something in me wants to fall back to Kant's position that what
       | you do to anything you do to yourself.
        
         | movpasd wrote:
         | Regarding LLM's performances on brownfield projects, I thought
         | of Naur's "Programming as Theory Building". He explains an
         | example of a compiler project that is taken over by a team
         | without guidance from the original developers:
         | 
         | > "at [the] later stage the original powerful structure was
         | still visible, but made entirely ineffective by amorphous
         | additions of many different kinds"
         | 
         | Maybe a way of phrasing it is that accumulating a lot of "code
         | quality capital" gives you a lot more leverage over technical
         | debt, but eventually it does catch up.
        
         | htx80nerd wrote:
         | I spent ~6hrs with Claude trying to fix a web worker bug in a
         | small JS code base Claude made. In the end it failed and I ran
         | out of credits. Claude kept wanting to rip out huge blocks of
         | code and replace entire functions. We never got any closer to a
         | solution. The Claude hype is unreal. My 'on the ground'
         | experience has been vastly different.
        
           | kuboble wrote:
           | Yes, you can get a project with claude to a state of
           | unrecoverable garbage. But with a little experience you can
           | learn what it's good at and this happens less and less.
        
           | zjp wrote:
           | That isn't my experience. My code and bug tracker are public,
           | so I have the privilege of being able to paste URLs to
           | tickets into Claude Code with the prompt "what the fuck?" and
           | it usually comes up with something workable on its own.
        
       | kittikitti wrote:
       | Another trash article from the New York Times, who financially
       | benefit from this type of content because of their ongoing
       | litigation against OpenAI. I think the assumption that developers
       | don't code is wrong. Most software engineers don't even want to
       | code, they are opportunists looking to make money. I have yet to
       | experience this cliff of coding. These people aren't asking for
       | hard enough questions. I have a bunch of things I want AI to
       | build that it completely fails on.
       | 
       | The article could have been written from a very different
       | perspective. Instead, the "journalists" likely interviewed a few
       | insiders from Big Tech and generalized. They don't get it. They
       | never will.
       | 
       | Before the advent of ChatGPT, maybe 2 in 100 people could code. I
       | was actually hoping AI would increase programming literacy but it
       | didn't, it became even more rare. Many journalists could have
       | come at it from this perspective, but instead painted doom and
       | gloom for coders and computer programming.
       | 
       | The New York Times should look in the mirror. With the advent of
       | the iPad, most experts agreed that they would go out of business
       | because a majority of their revenue came from print media. Look
       | what happened.
       | 
       | Understand this, most professional software and IT engineers hate
       | coding. It was a flex to say you no longer code professionally
       | before ChatGPT. It's still a flex now. But it's corrupt
       | journalism when there is a clear conflict of interest because the
       | NYT is suing the hell out of AI companies.
        
         | hn_acc1 wrote:
         | Agreed - just like the Fortune article talking about (Edit:
         | Morgan Stanley, not GS) saying "the AI revolution is coming
         | next year, and will decimate tons of industries, and no one is
         | ready for it". They quote Altman and Musk. Gee - what did you
         | expect from those two snake-oil salesmen?
        
         | novemberYankee7 wrote:
         | Also the fact that NYT gives all their devs licenses to Cursor
         | and Claude
        
       | htx80nerd wrote:
       | You have to hold AI hand to do even simple vanilla JS correctly.
       | Or do framework code which is well documented all over the net. I
       | love AI and use it for programming a lot, but the limitations are
       | real.
        
         | keeganpoppen wrote:
         | that's just not even remotely my experience. and i am ~20k
         | hours into my programming career. ai makes most things so much
         | faster that it is hard to justify _ever_ doing large classes of
         | things yourself (as much as this hurts my aesthetic
         | sensibilities, it simply is what it is).
        
           | lumost wrote:
           | Part of this depends on if you care that the AI wrote the
           | code "your way." I've been in shops with rather exotic and
           | specific style guides and standards which the AI would not or
           | will not conform to.
        
             | localhost wrote:
             | then have ai write a deterministic transformation tool that
             | turns it into the specific style and standard that is
             | needed
        
             | igor47 wrote:
             | Yeah, I also highly value consistency in my projects, which
             | forces me to keep an eye on the LLM and steer it often.
             | This limits my overall velocity especially on larger
             | features. But I'm still _much_ faster with the agent.
             | Recent example, https://github.com/igor47/csheet/pull/68 --
             | this took me a couple of hours pairing with Claude code,
             | which is insane give the size of the work here. Though this
             | PR creates a bunch of tables, routes, services -- it's not
             | just greenfield CRUD work. We're figuring out how to model
             | a complicated domain, integrating with existing code,
             | thinking through complex integrations including with LLMs
             | at run time. Claude is writing almost all the code, I'm
             | just steering
        
           | leptons wrote:
           | I've never seen a human estimate their "programming career"
           | in kilohours. Is that supposed to look more impressive than
           | years? So, you've been programming only about 7 years? I
           | guess I'm at about "170 kilohours".
        
             | kennywinker wrote:
             | I think it's probabky because of the malcom gladwell "ten
             | thousand hours" idea.
        
             | ralferoo wrote:
             | As well as the peer comment about Gladwell (10k hours is
             | considered the point you've mastered a skill), it's also a
             | far more honest metric about how much time you've spent
             | actually programming.
             | 
             | Maybe you were writing code, make design choices and
             | debugging 8 hours a day. Maybe you were primarily doing
             | something else and only writing code for an hour a day. Who
             | would be the better programmer? The first guy with one year
             | of experience or the second guy with 7 years?
             | 
             | I personally would only measure my experience in years,
             | because it's approaching 3 decades full-time in industry
             | (plus an additional decade of cutting my teeth during
             | school and university), but I can certainly see that
             | earlier on in a career it's a useful metric in comparison
             | to the 10,000 hours.
        
               | hrimfaxi wrote:
               | > Maybe you were writing code, make design choices and
               | debugging 8 hours a day. Maybe you were primarily doing
               | something else and only writing code for an hour a day.
               | Who would be the better programmer? The first guy with
               | one year of experience or the second guy with 7 years?
               | 
               | So your logic is that the grandparent specified hours
               | because they spent that many hours specifically
               | programming, and not by just multiplying the number of
               | years by the number of hours in a year?
        
               | ralferoo wrote:
               | I don't know exactly how they arrived at their 20k hours
               | figure, all I'm saying is that it didn't seem a
               | controversial way of expressing their experience level,
               | and assumed it was intended to be a comparison to the
               | typical 10k hours needed for mastery of a craft.
        
         | seanmcdirmid wrote:
         | Not in my experience. But then again, lots of programmers are
         | limited in how they use AI to write code. Those limitations are
         | definitely real.
        
         | GalaxyNova wrote:
         | Not what I've experienced
        
         | sp00chy wrote:
         | Exactly that is also my experience also with Claude Code. It
         | can create a lot of stuff impressively but with LOTS of more
         | code than necessary. It's not really effective in the end. I
         | have more than 35 years of coding experience and always dig
         | into the newest stuff. Quality wise it's still not more than
         | junior dev stuff even with latest models, sorry. And I know how
         | to talk to these machines.
        
           | TuxSH wrote:
           | I don't have as many years of professional experience as you
           | do, but IMO code pissing is one of the areas LLMs and
           | "agentic tools" shine the _least_.
           | 
           | In both personal projects and $dayjob tasks, the highest
           | time-saving AI tasks were:
           | 
           | - "review this feature branch" (containing hand-written
           | commits)
           | 
           | - "trace how this repo and repo located at ~/foobar use
           | {stuff} and how they interact with each other, make a Mermaid
           | diagram"
           | 
           | - "reverse engineer the attached 50MiB+ unstripped ELF
           | program, trace all calls to filesystem functions; make a
           | table with filepath, caller function, overview of what caller
           | does" (the table is then copy-pasted to Confluence)
           | 
           | - basic YAML CRUD
           | 
           | Also while Anthropic has more market share in B2B, their
           | model seems optimized for frontend, design, and literary work
           | rather than rigorous work; I find it to be the opposite with
           | their main competitor.
           | 
           | Claude writes code rife with safety issues/vulns all the
           | time, or at least more than other models.
        
           | iamflimflam1 wrote:
           | Try the new /simplify command.
        
         | wek wrote:
         | This is not my experience either. If you put the work in
         | upfront to plan the feature, write the test cases, and then
         | loop until they pass... you can build a lot of high quality
         | software quickly. The difference between a junior engineer
         | using it and a great architect using it is significant. I think
         | of it as an amplifier.
        
           | Mars008 wrote:
           | > The difference between a junior engineer using it and a
           | great architect using it is significant
           | 
           | Yes, juniors are trying to use AI with the minimum input.
           | This alone tells a lot..
        
           | bluefirebrand wrote:
           | This honestly reads to me like "if you spend a lot of time
           | doing tedious monotonous shit you can save a lot of time on
           | the interesting stuff"
           | 
           | I have no interest being a "great architect" if architects
           | don't actually _build anything_
        
             | hrimfaxi wrote:
             | "If I had eight hours to chop down a tree, I'd spend six
             | sharpening my axe" - Abraham Lincoln
        
           | andrekandre wrote:
           | > If you put the work in upfront to plan the feature, write
           | the test cases, and then loop until they pass...
           | 
           | it can be exhausting and time consuming front-loading things
           | so deeply though; sometimes i feel like i would have been
           | faster cutting all that out and doing it myself because in
           | the doing you discover a lot of missing context (in the spec)
           | anyways...
        
           | grey-area wrote:
           | I'm amazed at how many great architects and experts on AI we
           | now have.
        
         | moezd wrote:
         | AI assisted code can't even stick to the API documentation,
         | especially if the data structures are not consistent and have
         | evolved over time. You would see Claude literally pulling
         | function after function from thin air, desperately trying to
         | fulfill your complicated business logic and even when it's
         | complete, it doesn't look neat at all. Yes, it will have test
         | coverage, but one more feature request will probably break the
         | back of the camel. And if you raise that PR to the rest of your
         | team, good luck trying to summarise it all to your colleagues.
         | 
         | However if you just have an easy project, or a greenfield
         | project, or don't care about who's going to maintain that stuff
         | in 6 months, sure, go all in with AI.
        
           | ccosky wrote:
           | I definitely wonder if the people going all-in on AI
           | harnessing are working on greenfield projects, because it
           | seems overwhelming to try to get that set up on a brownfield
           | codebase where the patterns aren't consistent and the code
           | quality is mixed.
        
           | tayo42 wrote:
           | So just iterate on it? Your complaint is that the model isn't
           | one shotting the problem and reading your mind about style.
           | It's like any coding workflow, make it work, then make it
           | nice.
        
             | moezd wrote:
             | No, I never expect AI to one-shot (if I see such a miracle,
             | it's usually because I needed a one-liner or something
             | really simple and well documented, which I can also write
             | on the whiteboard from memory).
             | 
             | Try iterating over well known APIs where the response
             | payloads are already gigantic JSONs, there are multiple
             | ways to get certain data and they are all inconsistent and
             | Claude spits out function after function, laying waste to
             | your codebase. I found no amount of style guideline
             | documents to resolve this issue.
             | 
             | I'd rather read the documentation myself and write the code
             | by hand rather than reviewing for the umpteenth time when
             | Claude splits these new functions between e.g. __init__.py
             | and main.py and god knows where, mixing business logic with
             | plumbing and transport layers as an art form. God it was
             | atrocious during the first few months of FastMCP.
        
         | jcranmer wrote:
         | I must say, I do love how this comment has provoked such
         | varying responses.
         | 
         | My own observations about using AI to write code is that it
         | changes my position from that of an author to a reviewer. And I
         | find code review to be a much more exhausting task than writing
         | code in the first place, especially when you have to work out
         | how and why the AI-generated code is structured the way it is.
        
           | thegrim33 wrote:
           | There's a very wide range of programming tasks of differing
           | difficulty that people are using / trying to use it for, and
           | a very wide range of intelligence amongst the people that are
           | using / trying to use it, and who are evaluating its results.
           | Hence, different people have very different takes.
        
           | seanmcdirmid wrote:
           | > especially when you have to work out how and why the AI-
           | generated code is structured the way it is.
           | 
           | You could just ask it? Or you don't trust the AI to answer
           | you honestly?
        
             | chmod775 wrote:
             | You're anthropomorphizing.
             | 
             | LLMs can't lie nor can they tell the truth. These concepts
             | just don't apply to them.
             | 
             | They also cannot tell you what they were "thinking" when
             | they wrote a piece of code. If you "ask" them what they
             | were thinking, you just get a plausible response, not the
             | "intention" that may or may not have existed in some
             | abstract form in some layer when the system selected
             | tokens*. That information is gone at that point and the LLM
             | has no means to turn that information into something a
             | human could understand anyways. They simply do not have
             | what in a human might be called metacognition. For now.
             | There's lots of ongoing experimental research in this
             | direction though.
             | 
             | Chances are that when you ask an LLM about their output,
             | you'll get the response of either someone who now
             | recognized an issue with their work, or the likeness of
             | someone who believes they did great work and is now
             | defending it. Obviously this is based on the work itself
             | being fed back through the context window, which will
             | inform the response, and thus it may not be entirely
             | useless, but... this is all very far removed from what a
             | conscious being might explain about their thoughts.
             | 
             | The closest you can currently get to this is reading the
             | "reasoning" tokens, though even those are just some
             | selected system output that is then fed back to inform
             | later output. There's nothing stopping the system from
             | "reasoning" that it should say A, but then outputting B.
             | Example: https://i.imgur.com/e8PX84Z.png
             | 
             | * One might say that the LLM itself always considers
             | _every_ possible token and assigns weights to them, so
             | there wouldn 't even be a single chain of thought in the
             | first place. More like... every possible "thought" at the
             | same time at varying intensities.
        
               | pipes wrote:
               | Or ask another model to tell you what the changes do.
        
               | chmod775 wrote:
               | Did you mean to reply to some other comment? I'm having
               | trouble contextualizing your response - pardon the pun.
        
               | cyclopeanutopia wrote:
               | And you could first read the thing to which you are
               | replying. Don't tell me it was too long.
        
               | seanmcdirmid wrote:
               | It was too long, but thankfully AI can summarize so it's
               | no excuse anymore.
        
               | seanmcdirmid wrote:
               | I'm not anthropomorphizing. I've been in many situation
               | where the AI wrote some code some way and I had to ask
               | why, it told me why and then we moved on to better
               | solutions as needed. Better if it just wrote the code and
               | its reasoning was still in context, but even if it's not,
               | it can usually reverse engineer what it wrote well
               | enough. Then it's a conversation about whether there is a
               | better clearer way to do it, the code improves.
               | 
               | It sounds like you either have access to bad models or
               | you are just imagining what it's like to use an LLM in
               | this way and haven't actually tried asking it why it
               | wrote something. The only judgement you need to make is
               | the explanation makes sense or not, not some technical or
               | theoretical argument about where the tokens in the
               | explanation come from. You just ask questions until you
               | can easily verify things for yourself.
               | 
               | Also, pretending that the LLM is still just token
               | predicting and isn't bringing in a lot of extra context
               | via RAG and using extra tokens for thinking to answer a
               | query is just way out there.
        
               | chmod775 wrote:
               | You just steamrolled on, pretty much ignoring the comment
               | you are replying to, made unkind assumptions, and put
               | words in my mouth to boot. I don't mind some aggressive
               | argumentation, but this misses the mark so completely
               | that I have really no idea how to have a constructive
               | conversation this way.
               | 
               | > where the AI wrote some code some way and I had to ask
               | why, it told me why
               | 
               | I just explained that it cannot tell you why. It's simply
               | not how they work. You might as well tell me that it
               | cooked you dinner and did your laundry.
               | 
               | > the code improves.
               | 
               | We can agree on this. The iterative process works. The
               | understanding of it is incorrect. If someone's
               | understanding of a hammer superficially is "tool that
               | drives pointy things into wood", they'll inevitably try
               | to hammer a screw at some point - which might even work,
               | badly.
               | 
               | > It sounds like you either have access to bad models or
               | you are just imagining what it's like to use an LLM in
               | this way
               | 
               | Quoting this is really enough. You may imagine me
               | sighing.
               | 
               | > Also, pretending that the LLM is still just token
               | predicting
               | 
               | Strawman.
               | 
               | Overall your comment is dancing around engaging with what
               | is being said, so I will not waste my time here.
        
           | tayo42 wrote:
           | Your always reviewing code though. Either a team mates pr or
           | maybe your own code in 3 months, or some legacy thing.
        
             | christophilus wrote:
             | Human code is still easier to review. Also, I program 80%
             | of the time and review PRs 20% of the time. With AI, that
             | becomes: I review 80% of the time, and write markdown and
             | wait 20% of the time.
        
         | fudfomo wrote:
         | Most of this thread is debating whether models are good or bad
         | at writing code... however, I think a more important question
         | is what we feed the AI with because that dramatically
         | determines the quality of the output.
         | 
         | When your agent explores your codebase trying to understand
         | what to build, it read schema files, existing routes, UI
         | components etc... easily 50-100k tokens of implementation
         | detail. It's basically reverse-engineering intent from code.
         | With that level of ambiguous input, no wonder the results feel
         | like junior work.
         | 
         | When you hand it a structured spec instead including data
         | model, API contracts, architecture constraints etc., the agent
         | gets 3-5x less context at much higher signal density. Instead
         | of guessing from what was built it knows exactly what to build.
         | Code quality improves significantly.
         | 
         | I've measured this across ~47 features in a production codebase
         | with amedian ratio: 4x less context with specs vs. random agent
         | code exploration. For UI-heavy features it's 8-25x. The agent
         | reads 2-3 focused markdown files instead of grepping through
         | hundreds of KB of components.
         | 
         | To pick up @wek's point about planning from above: devs who get
         | great results from agentic development aren't better prompt
         | engineers... they're better architects. They write the spec
         | before the code, which is what good engineering always was...
         | AI just made the payoff for that discipline 10x more visible.
        
         | xtracto wrote:
         | The other day I (well, the AI) just wrote a Rust app to merge
         | two (huge, GB of data) tables by discovering columns with data
         | in common based on text distance (levenshtein and Dice) . It
         | worked beautifully
         | 
         | An i have NEVER made one line of Rust.
         | 
         | I dont understand nay-sayers, to me the state of gen.AI is like
         | the simpsons quote "worst day so far". Look were we are within
         | 5 years of the first real GPT/LLM. The next 5 years are going
         | to be crazy exciting.
         | 
         | The "programmer" position will become a "builder". When we've
         | got LLMs that generate Opus quality text at 100x speed (think,
         | ASIC based models) , things will get crazy.
        
           | npinsker wrote:
           | Human minds are built to find patterns, and you should be
           | careful not to assume the rate of improvement will continue
           | forever based on nothing but a pattern.
        
             | fauchletenerum wrote:
             | The overall trend in AI performance will still be up and to
             | the right like everything else in computing over the past
             | 50 years, improvement doesn't have to be linear
        
               | swingboy wrote:
               | Assuming newer, more efficient architectures are
               | discovered.
        
             | throwawaytea wrote:
             | Just the fact that even retail quality hardware is still
             | improving at local LLM significantly is still a great sign.
             | If AI quality remained the same, and the cost for local
             | hardware dropped to $1000, it would still be the greatest
             | thing since the internet IMO. So even if the worst happens
             | and all progress stops, I'm still very happy with what we
             | got.
        
               | leptons wrote:
               | >I'm still very happy with what we got
               | 
               | "One person's _slop_ is another person 's treasure"
               | 
               | I'm not all that impressed with "AI". I often "race" the
               | AI by giving it a task to do, and then I start coding my
               | own solution in parallel. I often beat the AI, or deliver
               | a better result.
               | 
               | Artificial Intelligence is like artificial flavoring.
               | It's cheap and tastes passable to most people, but real
               | flavors are far better in every way even if it costs
               | more.
        
               | LadyCailin wrote:
               | At their current stage, this feels like the wrong way to
               | use them. I use them fully supervised, (despite the fact
               | that feels like I'm fighting the tools), which is kind of
               | the best of both worlds. I review every line of code
               | before I allow the edit, and if something is wrong, I
               | tell it to fix it. It learns over time, especially as I
               | set rules in memories, and so the process has sped up, to
               | the point that this goes way faster than if I would have
               | done that myself. Not all tasks are appropriate for LLMs
               | at all, but when they are, this supervised mode is quite
               | fast, and I don't believe the output to be slop, but
               | anyways I feel like I own every line of code still.
        
               | cyberpunk wrote:
               | The happy path for me is with erlang, due to the
               | concurrency model the blast radius of an error is
               | exceptionally small, so the programming style is to let
               | things crash if they go wrong. So, really you are writing
               | the happy path code only (most of the time). Combine this
               | approach with some very robust tests (does this thing
               | pass the tests / behave how we need it to?) then you're
               | close to the point of not really caring about the
               | implementation at all.
               | 
               | Of course, i still do, but i could see not caring being
               | possible down the road with such architectures..
        
               | throwawaytea wrote:
               | Home made food is better than anything you can buy too.
               | Im 40 but I still drive 30 minutes to my parents once a
               | week for dinner because the food they make feels like the
               | elixir of life compared to the slop I can buy in trader
               | joes, Costco, or most restaurants.
               | 
               | But I'm pretty glad trader joes exists too.
        
           | sjeiuhvdiidi wrote:
           | Let me explain the naysayers, they know "programmer" has
           | always meant "builder" and just because search is better and
           | you can copy and paste faster doesn't mean you've built
           | anything.First thing people need to realize is no proprietary
           | code is in those databases, and using Ai will ultimately just
           | get you regurgitated things people don't really care about.
           | Use it all you want, you won't be able to do anything
           | interesting, they aren't giving you valuable things for free.
           | Anything of value will still take time and knowledge. The
           | marketing hype is to reduce wages and prevent competition. Go
           | for it.
        
           | fastforwardius wrote:
           | I seem to remember doing it in SQL (EDIT_DISTANCE) 20ish
           | years ago. While I wouldn't say it worked beautifully, I also
           | didn't need to make a single line of Rust :) also no more
           | than 2 line s of SQL were needed.
        
             | jqbd wrote:
             | And how many years of experience you needed to know what to
             | write, and what if you can replace that time with how long
             | prompting takes?
        
               | fastforwardius wrote:
               | It's an interesting question.
               | 
               | Years of school (reading, calculus etc) to get to the
               | point of learning basics of set theory. One day to learn
               | basic SQL based on understanding the set theory. Maybe
               | few weeks of using SQL at work for ad hoc queries to be
               | proficient enough (the query itself wasn't really
               | complex).
               | 
               | For the domain itself I was consulting experts to see
               | what matters.
               | 
               | I'm not sure that time it would take to know what to
               | prompt and verify the results is much different.
               | 
               | Fun fact - management decided that SQL solution wasn't
               | enerprisely enough so they hired external consultants to
               | build a system doing essentialy that but in Java + formed
               | an 8 people internal team to guide them. I heard they
               | finished 2 years later with a lot of manual matching.
        
           | dannersy wrote:
           | Because if you don't know the language or problem space,
           | there are footguns in there that you can't find, you won't
           | know what to look for to find them. Only until you try to
           | actually use this in a production environment will the issues
           | become evident. At that point, you'll have to either know how
           | to read and diagnose the code, or keep prompting till you fix
           | it, which may introduce another footgun that you didn't know
           | that you didn't know.
           | 
           | This is what gets me. The tools can be powerful, but my job
           | has become a thankless effort in pointing out people's
           | ignorance. Time and again, people prompt something in a
           | language or problem space they don't understand, it "works"
           | and then it hits a snag because the AI just muddled over a
           | very important detail, and then we're back to the drawing
           | board because that snag turned out to be an architectural
           | blunder that didn't scale past "it worked in my very
           | controlled, perfect circumstances, test run." It is getting
           | really frustrating seeing this happen on repeat and instead
           | of people realizing they need to get their hands dirty, they
           | just keep prompting more and more slop, making my job more
           | tedious. I am basically at the point where I'm looking for
           | new avenues for work. I say let the industry just run rampant
           | with these tools. I suspect I'll be getting a lot of job
           | offers a few years from now as everything falls apart and
           | their $10k a day prompting fixed one bug to cause multiple
           | regressions elsewhere. I hope you're all keeping your skills
           | sharp for the energy crisis.
        
             | psyklic wrote:
             | Before LLMs, I've watched in horror as colleagues
             | _immediately_ copy-paste-ran Stack Overflow solutions in
             | terminal, without even reading them.
             | 
             | LLM agents are basically the same, except now everyone is
             | doing it. They copy-paste-run lots of code without
             | meaningfully reviewing it.
             | 
             | My fear is that some colleagues are getting more skilled at
             | prompting but less skilled at coding and writing. And the
             | prompting skills may not generalize much outside of certain
             | LLMs.
        
           | zeroonetwothree wrote:
           | The less you know about a domain/language the better AI seems
           | to be :)
        
           | snozolli wrote:
           | _The next 5 years are going to be crazy exciting._
           | 
           | I don't want exciting. I want a stable, well-paying job that
           | allows me to put food on the table, raise a family with a
           | sense of security and hope, and have free time.
        
         | neversupervised wrote:
         | It's crazy how some people feel the ai and others don't. But
         | one group is wrong. It's a matter of time before everyone feels
         | the AI.
        
       | lelanthran wrote:
       | This is a very one-sided article, unashamedly so.
       | 
       | Where's the references to the decline in quality and embarrassing
       | outages for Amazon, Microsoft, etc?
        
         | dboreham wrote:
         | Everything you read is in service of someone's business model.
        
           | gnz11 wrote:
           | What's your point? Journalists have jobs?
        
             | 0xcafefood wrote:
             | NYT doesn't like digital advertisers and the programmers
             | who make that possible. They're directly in competition.
        
             | negromcnig wrote:
             | journalists are like our own simon willinson: they need to
             | put food on their plate by networking with powerful
             | entities that fly them out to conferences
        
         | esafak wrote:
         | Do we know that it decreased the quality, or introduced more
         | opportunities for bugs by simply increasing the velocity? If
         | every commit has a fixed probability of having a bug, you'll
         | run into more bugs in a week by going faster.
        
           | pydry wrote:
           | Do we know it increased the velocity and didnt just churn
           | more slop?
           | 
           | Even before AI the limiting factor on all of the teams I ever
           | worked on was bad decisions, not how much time it took to
           | write code. There seem to be more of those these days.
        
           | lelanthran wrote:
           | > Do we know that it decreased the quality, or introduced
           | more opportunities for bugs by simply increasing the
           | velocity?
           | 
           | That's an easy question to answer - you can look at outages
           | per feature released.
           | 
           | You may be instead looking at outages per loc written.
        
           | leptons wrote:
           | AI is _constantly_ trying to introduce bugs into my code. I
           | 've started disabling it when I know exactly where I'm going
           | with the code, because the AI is often a lot more confused
           | than I am about where the code is going.
        
       | fixxation92 wrote:
       | Conversations of the future...
       | 
       | "Can you believe that Dad actually used to have to go into an
       | office and type code all day long, MAUALLY??! Line by line, with
       | no advice from AI, he had to _think_ all by himself! "
        
         | aleph_minus_one wrote:
         | > "Can you believe that Dad actually used to have to go into an
         | office and type code all day long, MAUALLY??! Line by line,
         | with no advice from AI, he had to _think_ all by himself! "
         | 
         | Grumpy old man: "That's exactly why our generation was so much
         | smarter than today's whippersnappers: we were thinking from
         | morning to night the whole long day."
        
           | duskdozer wrote:
           | >What's ~~a computer~~ thinking?
        
         | ares623 wrote:
         | More likely:
         | 
         | "Dad, I've sent out 1000 applications and haven't had a call
         | back. I can't take it anymore. Has it always been like this?"
         | 
         | The Dad: It's not my fault!
        
         | allenu wrote:
         | I was thinking about that recently. Maybe decades from now
         | people will look at things like the Linux kernel or Doom and be
         | shocked that mere humans were able to program large codebases
         | by hand.
        
           | iamflimflam1 wrote:
           | It must have been:
           | 
           | Aliens Atlanteans Time travellers A hoax ...
        
           | johnisgood wrote:
           | Hmm, can you think of anything that we could do decades ago
           | but cannot do it now, today?
        
             | c0_0p_ wrote:
             | Fly supersonic commercially is the only thing I can think
             | of
        
             | allenu wrote:
             | I was being a little facetious, but there are things that
             | most people would find tedious today that we would put up
             | with in the past. Writing anything long by hand (letters,
             | essays), doing accounting without a spreadsheet, writing a
             | game in only assembly language, using punch cards,
             | typesetting newspapers and books manually...
        
         | bitwize wrote:
         | This was literally part of the premise of _The Jetsons_. George
         | 's job was to press a single button while the computer RUDI did
         | all the work.
         | 
         | The difference is, _Jetsons_ wasn 't a dystopia (unlike the
         | current timeline), so when Mr. Spacely fired George, RUDI would
         | take his side and refuse to work until George was re-hired.
        
         | bot403 wrote:
         | I had to run Jenkins to build my code. In the snow. And uphill
         | on git pull and deploy.
        
       | lagrange77 wrote:
       | It's really time that mainstream media picks up on 'agentic
       | coding' and the implications of writing software becoming a
       | commodity.
       | 
       | I'm an engineer (not only software) by heart, but after seeing
       | what Opus 4.6 based agents are capable of and especially the rate
       | of improvement, i think the direction is clear.
        
         | thrawa8387336 wrote:
         | I like 4.6 and agents based on it but can only qualify it as
         | moderately useful.
        
       | CollinEMac wrote:
       | >but like most of their peers now, they only rarely write code.
       | 
       | Citation needed. Are most developers "rarely" writing code?
        
         | dboreham wrote:
         | In my direct experience this is mostly true.
        
         | thrawa8387336 wrote:
         | And was true before AI
        
         | jcranmer wrote:
         | I'd expect that probably less than 10% of my time is spent
         | _actually_ writing code, and not because of AI, but because
         | enough of it is spent analyzing failures, reading documents,
         | participating in meetings, putting together presentations,
         | answering questions, reading code, etc. And even when I have a
         | nice, uninterrupted coding session, I still spend a decent
         | fraction of that time thinking through the design of how I want
         | the change rather than actually writing the code to effect that
         | change.
        
         | habinero wrote:
         | Yeah, actually writing code is a surprisingly small part of the
         | job.
        
       | fraywing wrote:
       | I keep getting stuck on the liability problem of this supposed
       | "new world". If we take this as far as it goes: AI agent
       | societies that designs, architects, and maintains the entire
       | stack E2E with little to no oversight. What happens when rogue
       | AIs do bad things? Who is responsible? You have to have fireable
       | senior engineers that understand deep fundamentals to make sure
       | things aren't going awry, right? /s
        
         | suzzer99 wrote:
         | Check out the movie Brazil, if you haven't seen it already.
         | Incredibly far ahead of its time.
        
       | comrade1234 wrote:
       | Having an AI is like having a dedicated assistant or junior
       | programmer that sometimes has senior-level insights. I use it to
       | do tedious tasks where I don't care about the code - like today I
       | used it to generate a static web page that let me experiment with
       | the spring-ai chat bot code I was writing - basic. But yesterday
       | it was able to track down the cause of a very obscure bug having
       | to do with a pom.xml loading two versions of the same library -
       | in my experience I've spent a full day on that type of bug and
       | Claud was able to figure it out from the exception in just
       | minutes.
       | 
       | But when I've used AI to generate new code for features I care
       | about and will need to maintain it's never gotten it right. I can
       | do it myself in less code and cleaner. It reminds me of code in
       | the 2000s that you would get from your team in India - lots of
       | unnecessary code copy-pasted from other projects/customers (I
       | remember getting code for an Audi project that had method names
       | related to McDonalds)
       | 
       | I think though that the day is coming where I can trust the code
       | it produces and at that point I'll just by writing specs. It's
       | not there yet though.
        
         | andoando wrote:
         | For any non professional work its there for me.
         | 
         | Wire up authentication system with sso. done Setup websockets,
         | stream audio from mic, transcribe with elvenlabs. done.
         | 
         | Shit that would take me hours takes literally 5 mins.
        
           | leptons wrote:
           | All that stuff would take me about 5 minutes without AI.
           | Those are things with 10,000 examples all over the web. AI is
           | good at distilling the known solutions. But anything even
           | slightly out of the ordinary, it fails miserably. I'd much
           | rather write that code myself instead of spend an hour
           | convincing an AI to do it for me.
        
             | andoando wrote:
             | There is absolutely no way. Those tasks take 5 mins to do.
             | Itd be done by the time you read the documentation for
             | elvenlabs
        
               | gedy wrote:
               | You might be comparing people who know how to do
               | something vs those who don't.
        
             | andoando wrote:
             | Im curious though, what do you consider slightly out of the
             | ordinary that it fails to do?
        
               | lpnam0201 wrote:
               | Haven't tried Claude for this, but I can't think how it
               | could possibly do. I built a game bot using Win32 API to
               | send input and screen capture to OCR and some OpenCV to
               | recognize game elements. Dead simple and actually quite
               | boring and repeatitive after I worked on it for a while.
               | How could Claude agents possibly do this ? I did use
               | Claude to refer docs and API, though.
        
               | DennisP wrote:
               | That actually sounds like something Claude could do
               | pretty easily.
               | 
               | Yegge's book describes his coauthor's first vibe coding
               | project. It went through screenshots he'd saved of
               | youtube videos, read the time with OCR, looked up
               | transcripts, and generated video snippets with subtitles
               | added. (I think this was before youtube added subtitles
               | itself.) He had it done in 45 minutes.
               | 
               | And using agents to control other applications is pretty
               | common.
        
               | in_cahoots wrote:
               | My elementary schooler did this with pictures of his
               | stuffed animals last week. I helped a little bit, but
               | most of it was Claude. He's never coded before.
        
               | leptons wrote:
               | Great, and you've taught him to never learn to code.
               | That's not as great an achievment as you might think it
               | is.
        
             | coldtea wrote:
             | > _All that stuff would take me about 5 minutes without
             | AI._
             | 
             | No, it wouldn't. Merely finding the examples and deps would
             | take over an hour.
        
               | conartist6 wrote:
               | Back when, we'd just go write a blog post or SO answer so
               | the next person wouldn't suffer as much.
               | 
               | Thank god THOSE days are over and everyone just lets
               | everyone else suffer alone now
        
               | iijaachok wrote:
               | Yes, because search engines are populated with SEO-
               | optimized LLM-filled articles that say nothing of value
               | anymore. The only reason AI-assisted tools are "better"
               | is because Web search is so much worse.
        
               | mexicocitinluez wrote:
               | It's like everyone forgot that the first result for
               | anything web-related would be W3schools, and the next 5
               | would be spam message boards that tries to scrape all the
               | other boards and sends you to a porn site when you click
               | on it.
        
               | mrbombastic wrote:
               | Yeah it is worse now but I don't remember it ever being
               | good. If you know where to look and have a trusted set of
               | resources curated sure, but of course you won't for
               | unfamiliar territory which is exactly what LLMs help
               | with.
        
             | mexicocitinluez wrote:
             | > All that stuff would take me about 5 minutes without AI.
             | 
             | There isn't a single person on this planet (detractor or
             | not) that would believe this statement.
             | 
             | If you're argument rests on an insane amount of hyperbole
             | (that immediately comes off as just lying), then maybe it's
             | not a great argument.
             | 
             | > I'd much rather write that code myself instead of spend
             | an hour convincing an AI to do it for me.
             | 
             | You're not suggesting that asking CC to build the UI for a
             | route planner takes me an hour to type, are you?
        
               | ch4s3 wrote:
               | > There isn't a single person on this planet (detractor
               | or not) that would believe this statement.
               | 
               | It's so galling to see people say shit like this. It's
               | like the old build slack in a weekend trope.
        
               | leptons wrote:
               | >Wire up authentication system with sso.
               | 
               | Simple npm install, all of it has already been distilled
               | into dozens of similar repos. Just pick one, install it,
               | and follow the simple use case. 5 minutes if we're in a
               | race.
               | 
               | >done Setup websockets
               | 
               | If this takes you more than 5 minutes, then you're a shit
               | developer.
               | 
               | >stream audio from mic
               | 
               | Again, another npm install or two, simple POC could take
               | 5 minutes.
               | 
               | >transcribe with elvenlabs
               | 
               | I don't know what elvenlabs is, nor do I care, but I
               | doubt it's as complex as the OP thinks it is considering
               | the rest of their comment was about simple, solved
               | problems.
        
         | triyambakam wrote:
         | This is the take when you haven't really tried driving these
         | tools with much practice
        
           | nickjj wrote:
           | I don't think it's that
           | 
           | Here's an example from Gemini with some Lua code:
           | label = key:gsub("on%-", ""):gsub("%-", "
           | "):gsub("(%a)([%w_']*)", function(f, r)            return
           | f:upper() .. r:lower()          end)              if
           | label:find("Click") then           label =
           | label:gsub("(%a+)%s+(%a+)", "%2 %1")         elseif
           | label:find("Scroll") then           label =
           | label:gsub("(%a+)%s+(%a+)", "%2 %1")         end
           | 
           | I don't know Lua too well (which is why I used AI) but I know
           | programming well enough to know this logic is ridiculous.
           | 
           | It was to help convert "on-click-right" into "Right Click".
           | 
           | The first bit of code to extract out the words is really
           | convoluted and hard to reason about.
           | 
           | Then look at the code in each condition. It's identical.
           | That's already really bad.
           | 
           | Finally, "Click" and "Scroll" are the only 2 conditions that
           | can ever happen and the AI knew this because I explained this
           | in an earlier prompt. So really all of that code isn't
           | necessary at all. None of it.
           | 
           | What I ended up doing was creating a simple map and looked up
           | the key which had an associated value to it. No conditions or
           | swapping logic needed and way easier to maintain. No AI used,
           | I just looked at the Lua docs on how to create a map in Lua.
           | 
           | This is what the above code translated to:
           | local on_event_map = {           ["on-click"] = "Left Click",
           | ["on-click-right"] = "Right Click",           ["on-click-
           | middle"] = "Middle Click",           ["on-click-backward"] =
           | "Backward Click",           ["on-click-forward"] = "Forward
           | Click",           ["on-scroll-up"] = "Scroll Up",
           | ["on-scroll-down"] = "Scroll Down",         }
           | label = on_event_map[key]
           | 
           | IMO the above is a lot clearer on what's happening and super
           | easy to modify if another thing were added later, even if the
           | key's format were different.
           | 
           | Now imagine this. Imagine coding a whole app or a non-trivial
           | script where the first section of code was used. You'd have
           | thousands upon thousands of lines of gross, brittle code
           | that's a nightmare to follow and maintain.
        
         | kansface wrote:
         | I've generated 250KLoC this week, absolutely no changes in deps
         | or any other shenanigans. I'm not even really trying to
         | optimize my output. I work on plans/proposals with 2 or 3
         | agents simultaneously in Cursor while one does work, sometimes
         | parallelized. I can't do that in less code and cleaner. I can't
         | do it at all. Don't wait too long.
        
           | habinero wrote:
           | > I've generated 250KLoC this week
           | 
           | It's horrifying, all right, but not in the way you think lol.
           | If you don't understand why this isn't a brag, then my job is
           | very safe.
        
             | coldtea wrote:
             | If managers can't understand why this isn't a brag, then
             | your job is hardly safe.
        
               | motbus3 wrote:
               | Managers jobs are more at risk than senior engineers.
               | 
               | My company, and few others I know reduced the number of
               | managers by 90% or more.
        
               | kakacik wrote:
               | This. We moved to 'agile' roughly at same time llms
               | started coming. You know who is mostly missing from the
               | wider IT teams landscape now? Most of PMs and BAs, on
               | purpose. Who is keeping their work - devs or more like
               | devops, surprisingly testers (since our stuff seems
               | ridiculously complex to test well for many use cases and
               | we can't just break our bank by destroying production by
               | fast half-assed deliveries).
               | 
               | And then admins/unix/network/windows/support team, nobody
               | replacing those anytime soon. Those few PMs left are
               | there only for big efforts requiring organizing many
               | teams, and we rarely do those now.
               | 
               | I don't like it, chasing people, babysitting processes
               | and so on, but certainly just more work for me.
        
               | GeoAtreides wrote:
               | you're not responding to op's point, unless you're
               | insinuating there won't be any managers ever, which won't
               | happen. As long as there is one manager left, OP's point
               | remains.
        
               | ajb wrote:
               | Agents are new, but dumb coding practices are not.
               | Despite what it may seem, the knowledge of how to manage
               | development has increased. One practice I haven't seen
               | for a while is managing by limiting the number of lines
               | changed. (This was a dumb idea because rewriting a
               | function or module is sometimes the only way to keep it
               | comprehensible - I'm not talking about wholesale
               | rewriting, I'm talking about code becoming encrusted with
               | conditions because the devs are worried that changing the
               | structure would change too many lines)
        
             | sevenzero wrote:
             | Less is more, its not a hard thing to understand. These
             | companies are accumulating record level tech debt.
        
               | mexicocitinluez wrote:
               | I use these tools a lot, and one thing that has stood out
               | to me is that they LOVE to write code. A lot of it. And
               | they're not super great at extracting the reusable parts.
               | They also love to over-engineer things.
               | 
               | I've taken great pains to get by with as little code as
               | possible, because the more code you have, the harder it
               | is to change (obviously). And while there are absolutely
               | instances in which I'm not super invested in a piece of
               | code's ability to be changed, there are definitely
               | instances in which I am.
        
               | sevenzero wrote:
               | Yea, by my less is more logic its sometimes also
               | difficult to do. With that approach people try to become
               | clever and write shorter code thats unmaintainable due to
               | mental gymnastics other people have to go through when
               | reading it. What LLMs are doing is probably going for
               | some kind of overengineered "best practice" solution. I
               | personally only use them for simple Laravel CRUD apps and
               | they are admittedly pretty good at that.
        
           | MadxX79 wrote:
           | Your developers were so preoccupied with whether or not they
           | could, they didn't stop to think if they should (add 250kloc)
        
             | bot403 wrote:
             | I've worked with a type of (anti?) developer in my career
             | that seems to only be able to add code. Never change or
             | take it away. It's bizarre. There's some calculation bug,
             | then a few lines down some code which corrects it instead
             | of just fixing the original lines.
             | 
             | It's bizzare, and as horrible as you might imagine.
             | 
             | And it's been more than one or two people I've seen do
             | this.
        
               | MadxX79 wrote:
               | Now they have agents.
               | 
               | People need to understand that code is a liability. LLMs
               | hasn't changed that at all. You LLM will get every bit as
               | confused when you have a bug somewhere in the backend and
               | you then work around it with another line of code in the
               | front end. line of code
        
               | GoblinSlayer wrote:
               | They can always generate a new backend prototype from
               | scratch.
        
               | pram wrote:
               | This sounds like some kind of learned risk aversion, like
               | they don't want to assume the responsibility of altering
               | whats already there.
        
           | slopinthebag wrote:
           | LOL that's it? I generated over 5 million lines of code this
           | week. You need to step it up or you're gonna be left behind.
        
             | zahlman wrote:
             | You mean, you don't have                 yes \; >> main.c
             | 
             | running in the background 24/7?
        
             | kubb wrote:
             | I left an agent generating code over the weekend, so that I
             | can get to 15 million.
             | 
             | What code? Code!
        
           | zahlman wrote:
           | > I can't do that in less code and cleaner. I can't do it at
           | all.
           | 
           | Can't do _what_ , precisely?
        
         | thangalin wrote:
         | Syntax highlighting rules, initially vibe-coded 40 languages
         | and formats in about 10 minutes. What surprised me is when it
         | switched the design from a class to the far more elegant single
         | line of code:                   return \file_exists( $file ) ?
         | require $file : [];
         | 
         | *
         | https://repo.autonoma.ca/repo/treetrek/blob/HEAD/render/High...
         | 
         | The rules files:
         | 
         | *
         | https://repo.autonoma.ca/repo/treetrek/tree/HEAD/render/rule...
        
         | zazibar wrote:
         | >I think though that the day is coming where I can trust the
         | code it produces and at that point I'll just by writing specs.
         | It's not there yet though.
         | 
         | Must be nice to still have that choice. At the company I work
         | for they've just announced they're cancelling all subscriptions
         | to JetBrains, Visual Studio, Windsurf, etc. and forcing every
         | engineer to use Claude Code as a cost-saving measure. We've
         | been told we should be writing prompts for Claude instead of
         | working in IDEs now.
        
           | GoblinSlayer wrote:
           | Isn't Visual Studio a one time purchase?
        
           | the_real_cher wrote:
           | Thats insane!
        
           | swader999 wrote:
           | I didn't renew Jet Brains this month. Been a loyal customer
           | and would have quit jobs from 2008 onwards without it.
        
             | DennisP wrote:
             | Fwiw, IntelliJ at least has an MCP server so coding agents
             | can use the refactoring tools. Don't know about the other
             | JetBrains IDEs.
        
             | bredren wrote:
             | Me too.
             | 
             | I used to report bugs, read release notes; I was all in on
             | the full stack debug capability in pycharm of Django.
             | 
             | The first signs of trouble (with AI specifically) predated
             | GitHub copilot to TabNine.
             | 
             | TabNine was the first true demonstration of AI powered code
             | completion in pycharm. There was an interview where a
             | jetbrains rep lampooned AI's impact on SWE. I was an early
             | TabNine user, and was aghast.
             | 
             | A few months later copilot dropped, time passed and now
             | here we are.
             | 
             | It was neat figuring out how I had messed up my
             | implementations. But I would not trade the power of the CLI
             | AI for any *more* years spent painstakingly building
             | products on my own.
             | 
             | I'm glad I learned when I did.
        
           | kubb wrote:
           | Thoughts and prayers.
        
           | DennisP wrote:
           | Even if you're using Claude, canceling the IDEs might be poor
           | strategy. Steve Yegge points out in his book that the
           | indexing and refactoring tools in IDEs are helpful to AIs as
           | well. He mentions JetBrains in particular as working well
           | with AI. Your company's IDE savings could be offset by higher
           | token costs.
        
             | DennisP wrote:
             | Perhaps it would help if I include the quote, so from _Vibe
             | Coding_ pages 165-166:
             | 
             | > [IDEs index] your code base with sophisticated
             | proprietary analysis and then serve that index to any tool
             | that needs it, typically via LSP, the Language Services
             | Protocol. The indexing capabilities of IDEs will remain
             | important in the vibe coding world as (human) IDE usage
             | declines. Those indexes will help AIs find their way around
             | your code, like they do for you.
             | 
             | > ...It will almost always be easier, cheaper, and more
             | accurate for AI to make a refactoring using an IDE or
             | large-scale refactoring tool (when it can) than for AI to
             | attempt that same refactoring itself.
             | 
             | > Some IDEs, such as IntelliJ, now host an MCP server,
             | which makes their capabilities accessible to coding agents.
        
               | schubart wrote:
               | Would you recommend that book?
        
               | DennisP wrote:
               | Yes, it's fantastic. Hard to imagine a better resource
               | for getting started with vibe coding, on through
               | developing large high-quality projects with it. It
               | doesn't get into the details of particular tools much, so
               | it should stay relevant for a while.
        
           | mchaver wrote:
           | I wonder how much cost savings there are in the long term
           | when token prices go up, the average developer's ability to
           | code has atrophied, and the company code bases have turned
           | into illegible slop. I will continue to use LLMs cautiously
           | while working hard to maintain my ability to code in my off
           | time.
        
             | daveguy wrote:
             | You shouldn't have to maintain your ability to code in your
             | off time. Is your company one of those that's requiring AI
             | only coding?
        
           | gedy wrote:
           | Honestly while I know everyone needs a job, just speed run
           | all this crap and let the companies learn from making a big
           | unmaintainable ball of mud. Don't make the bad situation work
           | by putting in your good skills to fix things behind the
           | scenes, after hours, etc.
        
             | falkensmaize wrote:
             | Management has made it very clear that we're still
             | responsible for the code we push even if the llm wrote it.
             | So there will be no blaming Claude when things fall apart.
        
               | gedy wrote:
               | My personal line is they can't say that if you force devs
               | to use LLMs "and be quick about it"
        
           | qudat wrote:
           | That's going to give you all a ton of job security in a year
           | when we realize that prompt first yields terrible results for
           | maintainability.
        
             | kjkjadksj wrote:
             | Or they fire the existing staff who prompted this mess and
             | bring in mkinsey to glue the mess together
        
           | sobjornstad wrote:
           | This is completely insane, and that's coming from someone who
           | does 95% of edits in Claude Code now.
        
           | deadbabe wrote:
           | I hope they are prepared to pay the $500/month per head when
           | subsidies expire.
        
             | delecti wrote:
             | Realistically that's an increase of maybe a couple percent
             | of cost per employee. If it truly does end up being a force
             | multiplier, 2-5% more per dev is a bargain. I think it's
             | exceedingly unlikely that LLMs will replace devs for most
             | companies, but it probably will speed up dev work enough to
             | justify at _least_ a single-digit percent increase in per-
             | dev cost.
        
               | deadbabe wrote:
               | "speeding up dev work" is pointless to a company. That
               | benefit goes entirely to the developer and does not
               | trickle down well.
               | 
               | You might think "ok, we'll just push more workload onto
               | the developers so they stay at higher utilization!"
               | 
               | Except most companies do not have endless amounts of new
               | feature work. Eventually devs are mostly sitting idle.
               | 
               | So you think "Ha! Then we'll fire more developers and get
               | one guy to do everything!"
               | 
               | Another bad idea for several reason. For one, you are
               | increasing the bus factor. Two, most work being done in
               | companies at any given time is actually _maintenance_.
               | One dev cannot maintain everything by themselves, even
               | with the help of LLMs. More eyes on stuff means issues
               | get resolved faster, and those eyes need to have real
               | knowledge and experience behind them.
               | 
               | Speed is sexy but a poor trade off for quality code
               | architecture and expert maintainers. Unless you are a
               | company with a literal never ending list of new things to
               | be implemented (very few), it is of no benefit.
               | 
               | Also don't forget the outrage when Cursor went from
               | $20/month to $200/month and companies quickly cancelled
               | subscriptions...
        
               | sobjornstad wrote:
               | > Except most companies do not have endless amounts of
               | new feature work. Eventually devs are mostly sitting
               | idle.
               | 
               | At every place I have ever worked (as well as my personal
               | life), the backlog was 10 times longer than anyone could
               | ever hope to complete, and there were untold amounts of
               | additional work that nobody even bothered adding to the
               | backlog.
               | 
               | Some of that probably wouldn't materialize into real work
               | if you could stay more on top of it - some of the things
               | that eventually get dropped from the backlog were bad
               | ideas or would time out of being useful before they got
               | implemented even with higher velocity - but I think most
               | companies could easily absorb a 300% increase or more in
               | dev productivity and still be getting value out of it.
        
             | mekael wrote:
             | I've heard estimates of starting at 2k a month per person,
             | and thats for the "normal" user-base
        
             | gedy wrote:
             | They'll just skip raises and say it's part of your comp for
             | increasing your productivity or some tone-deaf BS
        
         | DennisP wrote:
         | I'm halfway through Steve Yegge's book _Vibe Coding_. Yegge was
         | quoted in the article:
         | 
         | > "We're talking 10 to 20 -- to even 100 -- times as productive
         | as I've ever been in my career," Steve Yegge, a veteran coder
         | who built his own tool for running swarms of coding agents
         | 
         | That tool has been pretty popular. It was a couple hundred
         | thousand lines of code and he wrote it in a couple months. His
         | book is about using AI to write major new projects and get them
         | reliable and production-ready, with clean, readable code.
         | 
         | It's basically a big dose of solid software engineering
         | practices, along with enough practice to get a feel for when
         | the AI is screwing up. He said it takes about a year to get
         | really good at it.
         | 
         | (Yegge, fwiw, was a lead dev at Amazon and Google, and a well-
         | known blogger since the early 2000s.)
        
       | xenadu02 wrote:
       | It's an accelerator. A great tool if used well. But just like all
       | the innovations before it that were going to replace programmers
       | it simply won't.
       | 
       | I used Claude just the other day to write unit test coverage for
       | a tricky system that handles resolving updates into a consistent
       | view of the world and handles record resurrection/deletion. It
       | wrote great test coverage _because it parsed my headerdoc and
       | code comments that went into great detail about the expected
       | behavior_. The hard part of that implementation was the prose I
       | wrote and the thinking required to come up with it. The actual
       | lines of code were already a small part of the problem space. So
       | yeah Claude saved me a day or two of monotonously writing up test
       | cases. That 's great.
       | 
       | Of course Claude also spat out some absolute garbage code using
       | reflection to poke at internal properties because the access
       | level didn't allow the test to poke at the things it wanted to
       | poke at, along with some methods that were calling themselves in
       | infinite recursion. Oh and a bunch of lines that didn't even
       | compile.
       | 
       | The thing is about those errors: most of them were a fundamental
       | inability to reason. They were technically correct in a sense. I
       | can see how a model that learned from other code written by
       | humans would learn those patterns and apply them. In some
       | contexts they would be best-practice or even required. But the
       | model can't reason. It has no executive function.
       | 
       | I think that is part of what makes these models both amazingly
       | capable and incredibly stupid at the same time.
        
       | gist wrote:
       | For one thing comments here appear to apply to the quality and
       | issues today not potentially going forward. Quality will change
       | quicker than anyone expects. I am wondering how many people at HN
       | remember when the first Mac came out with Mac Paint and then
       | Pagemaker or Quark. That didn't evolve anywhere nearly as quickly
       | as AI appears to be.
       | 
       | Also I am not seeing how anyone is considering that what a
       | programmer considers quality and what 'gets the job done' (as
       | mentioned in the article) matters in any business. (Example with
       | typesetting is original laser printers were only 300dpi but after
       | a short period became 1200dpi 'good enough' for camera ready
       | copy).
        
       | IntrepidPig wrote:
       | > "The reason that tech generally -- and coders in particular --
       | see L.L.M.s differently than everyone else is that in the
       | creative disciplines, L.L.M.s take away the most soulful human
       | parts of the work and leave the drudgery to you," Dash says. "And
       | in coding, L.L.M.s take away the drudgery and leave the human,
       | soulful parts to you."
       | 
       | This doesn't really make sense to me. GenAI ostensibly removes
       | the drudgery from other creative endeavors too. You don't need to
       | make every painstaking brushstroke anymore; you can get to your
       | intended final product faster than ever. I think a common
       | misunderstanding is that the drudgery is really inseparable from
       | the soulful part.
       | 
       | Also, I think GenAI in coding actually has the exact same failure
       | modes as GenAI in painting, music, art, writing, etc. The output
       | lacks depth, it lacks context, and it lacks an understanding of
       | its own purpose. For most people, it's much easier to intuitively
       | see those shortcomings of GenAI manifest in traditional creative
       | mediums, just because they come more naturally to us. For coding,
       | I suspect the same shortcomings apply, they just aren't as clear.
       | 
       | I mean, at the end of the day if writing code is just to get
       | something that works, then sure, let's blitz away with LLMs and
       | not bother to understand what we're doing or why we do it
       | anymore. Maybe I'm naive in thinking that coding has creative
       | value that we're now throwing away, possibly forever.
        
         | steve-atx-7600 wrote:
         | Maybe they mean more soulful like a fellow that blacksmiths his
         | own tools and metal fasteners prior to constructing something.
         | I'd personally think this person was a badass, but until wwiii,
         | it's so impractical and seems arbitrary because why stop there
         | - get more soulful and mine your own ore too.
        
       | sjeiuhvdiidi wrote:
       | It's all nonsense. It's just better search, intelligence in not
       | artificial. They are trying to convince everyone that they don't
       | need to pay programmers. That's all, all it is. It'll work on the
       | ignorant who'll take less money to make sure it works and fix the
       | bugs, which is mostly what they were paying for anyway. They just
       | want to devalue the work of the people they are reliant on.
       | Nothing new.
        
         | neversupervised wrote:
         | I think you're a bit behind on your world view. Just because
         | it's inconvenient to you that non coders can now code, doesn't
         | make it untrue.
        
           | mdavid626 wrote:
           | No, they can't.
           | 
           | It has nothing to do with inconvenience.
           | 
           | I really like that layman now make these statements - they
           | know better than people working in the industry for decades.
        
             | habinero wrote:
             | None of them understand the first thing about what the job
             | actually is, or they wouldn't try to brag about the 200K
             | LoC they generated lol
        
       | bryanrasmussen wrote:
       | how many times in the history of computer programming has there
       | been an end to computer programming as we know it, successfully,
       | and how many times predicted?
       | 
       | I can think of one successfully, off hand, although you could
       | probably convince me there was more than one.
       | 
       | the principle phrase being "as we know it", since that implies a
       | large scale change to how it works but it continues afterwards,
       | altered.
        
         | mech422 wrote:
         | Off the top of my head, I can think of the following during my
         | career:                  1. COBOL (we actually did still use it
         | back in the 80s)             2.AI back in the 80s (Dr. Dobbs
         | was all concerned about it ...)             3. RAD
         | 4. No-Code             5. Off-shoring             6. Web 2.0
         | 7. Web 3.0             8. possibly the ADA/provably correct
         | push depending on your area of programming
         | 
         | TBH - I think the AI's are nice tools, but they got a long way
         | to go before it's the 'end of computer programming as we know
         | it'
         | 
         | edit: formatting
        
           | kuboble wrote:
           | Stack overflow (and internet in general) changed the
           | programming as we (at least some of us) knew it.
           | 
           | When I was learning programming I had no internet, no books
           | outside of library, nobody to ask for days.
           | 
           | I remember vividly having spent days trying to figure out how
           | to use the stdlib qsort, and not being able to.
        
             | mech422 wrote:
             | Hmm - I'm not sure I'd say that 'changed programming' - but
             | the internet in general changed 'learning to program'. I
             | can remember when I first discovered gopher and found I
             | could read tons recent material for free, or finding
             | stonybrook on the web - that was like a gold mine of
             | algorithms! :-D
        
             | joefourier wrote:
             | I'm not from that generation so that's a bit hard for me to
             | understand. Even if you used a closed-source C compiler,
             | wouldn't you still have been able to look at the header
             | file, which would have been pretty self-explanatory?
             | 
             | E.g.
             | 
             | void qsort(void* base, size_t nmemb, size_t size, int (
             | _compar)(const void_ , const void* ));
             | 
             | And surely if you bought a C compiler, you would have
             | gotten a manual or two with it? Documentation from the pre-
             | Internet age tended to be much better than today.
        
               | mech422 wrote:
               | Yeah - but you have to be a good enough programmer to
               | really understand the headers.. the 'bootstrapping'
               | problem was real :-) Especially if you didn't live in a
               | metropolitan/college area. My local library was really
               | short on programming books - especially anything 'in
               | depth'. Also, 'C' was considered a "professional's
               | language" back then - so bookstores/libraries were more
               | likely to have books on BASIC then 'C'
        
               | rustyzig wrote:
               | What kind of modern C wizardry is that? qsort was:
               | qsort(base, nel, width, compar)         char *base;
               | int (*compar)();
        
           | fweimer wrote:
           | COBOL certainly had a lasting impact, but only for some
           | application domains. The rest didn't seem to be particularly
           | successful or impactful. Maybe RAD if you consider office
           | application macros and end user report generation in it.
           | (Spreadsheets extended programming to non-programmers and had
           | a long-lasting impact, but I wouldn't call them RAD.)
        
             | mech422 wrote:
             | Thats sorta the point... at one time or another, those were
             | all projected to be 'the end of programming as we know
             | it'...
             | 
             | Hell, COBOL's origins was in IBM wanting to make
             | programming an 'entry level' occupation.
             | 
             | Oddly enough, spreadsheets had a huge impact (and still run
             | a lot of companies behind the scenes :-P ) But I can't
             | remember anyone claiming they would 'end programming' ?
        
           | ralferoo wrote:
           | FWIW I worked for a company from 2002 to 2006 that still had
           | quite a large COBOL team even then. Some of the team members
           | were also in their 20s and they'd been hired and trained up
           | in COBOL.
        
             | mech422 wrote:
             | I started by working on back-end accounting systems - most
             | of those seemed to be COBOL ... or _SHUDDER_ RPG.
        
           | bryanrasmussen wrote:
           | OK, those are all ones that didn't change programming as we
           | know it, but some came closer than others right?
           | 
           | I definitely considered some of those in my list of failed
           | revolutions.
           | 
           | My one completely successful revolution is moving from punch
           | card programming.
        
             | mech422 wrote:
             | Oh yeah - thats a good one...
             | 
             | Maybe the move from teletype to CRT's as well ?
        
         | fweimer wrote:
         | What's the one successful one? Visicalc?
        
           | bryanrasmussen wrote:
           | I would say the one that definitely changed programming was
           | moving from the punch card era. A lot of these others that
           | people are mentioning I don't think really changed
           | programming, they just looked like they were going to.
        
         | rzmmm wrote:
         | Someone compared LLM in 2020s to GUI in 80s and 90s. Graphical
         | interfaces didn't replace text interface, but it just became
         | additional to it.
        
       | bikelang wrote:
       | If coding truly becomes effortless to produce - and by that
       | extension a product becomes near free to produce - then I find it
       | quite odd that the executive class thinks their businesses won't
       | be completely up ended by a raging sea of competition.
        
         | postsantum wrote:
         | The struggle will completely shift to how to get traffic
        
           | mirsadm wrote:
           | That is already the struggle. There is too much stuff
           | already.
        
             | GoblinSlayer wrote:
             | All that stuff is shit though.
        
               | delecti wrote:
               | Is _all_ of it shit, or you just can 't find the good
               | stuff? "The struggle will completely shift to how to get
               | traffic" is from the business side, and you're
               | experiencing it from the customer side.
        
         | bot403 wrote:
         | The markets seem to agree with you and are pricing accordingly.
        
         | EagnaIonat wrote:
         | All run of the mill software is gone or on borrowed time. Why
         | pay a subscription for a product that I can get something
         | Claude to build it for me.
         | 
         | Before I was building tools, now I am building full
         | applications in less time than I did before for tools.
         | 
         | What will be around for a while is where you need an expert in
         | the loop to drive the AI. For example enterprise applications.
         | You simply can't hand that off to an AI at this point.
        
           | dominotw wrote:
           | no one wants your vibecoded full applications though. not
           | sure why you are building them.
        
             | EagnaIonat wrote:
             | I am building them because I am using them to do my work
             | faster.
             | 
             | I'm not selling anything, but I can see the quality of what
             | is created and it is on-par with much of the stuff on the
             | App store.
             | 
             | No one would even notice that it is a co-creation unless I
             | mentioned the time to create it.
             | 
             | Just to be clear. Vibe coding implies that you are not
             | reviewing the code that is created, or even knowing what is
             | being created. That is not what is happening.
        
               | dominotw wrote:
               | > I am building them because I am using them to do my
               | work faster.
               | 
               | interesting. any examples you can share?
        
               | bdangubic wrote:
               | I used a bunch of tools from https://setapp.com/ and no
               | longer subscribe. I used to pay for Linear for all my
               | personal projects, built one with CC that perfectly fits
               | my needs... I also built a myriad of small tools that
               | help me automate bunch of busy work I used to do
               | manually, both for professional and personal projects
        
               | gedy wrote:
               | > I am building them because I am using them to do my
               | work faster.
               | 
               | You sound like CTO at my company rewriting stable
               | libraries in languages he is familiar with and calling it
               | 100x...
        
           | AstroBen wrote:
           | Can we see the applications?
        
             | xienze wrote:
             | ... no.
        
             | EagnaIonat wrote:
             | They are in work, so sorry no. But I can tell you started
             | off
             | 
             | - Getting Claude to do the work
             | 
             | - creating in python tools
             | 
             | - Docker apps
             | 
             | - XCode
        
         | some_random wrote:
         | No, that's exactly what at least some of them think and it's
         | why the market has been so volatile lately.
        
         | glaslong wrote:
         | They're going to have a fast and ruthless testing of whether
         | their product senses and abilities to attract and trap
         | customers were actually skill or lucky positioning, as
         | competition explodes from every direction, including from
         | within customer and user bases.
        
       | igor47 wrote:
       | I'm not normally a fan of the NYT but this wasn't too bad. It
       | passed the Gel-Mann test, and is clearly written by someone who
       | knows the field well, even though the selection of quotes skews
       | to towards outliers -- I think Yeggie for instance is pretty far
       | out of the mainstream in his views on LLMs, whether ahead or
       | sideways.
       | 
       | As a result a lot of the responses here are either quibbles or
       | cope disguised as personal anecdotes. I'm pretty worried about
       | the impact of the LLMs too, but if you're not getting use out of
       | them while coding, I really do think the problem is you.
       | 
       | Since people always want examples, I'll link to a PR in my
       | current hobby project, which Claude code helped me complete in
       | days instead of weeks. https://github.com/igor47/csheet/pull/68
       | Though this PR creates a bunch of tables, routes, services --
       | it's not just greenfield CRUD work. We're figuring out how to
       | model a complicated domain (the rules to DnD 5e, including the
       | 2014 and the 2024 revisions of those rules), integrating with
       | existing code, thinking through complex integrations including
       | with LLMs at run time. Claude is writing almost all the code, I'm
       | just steering
        
         | colkassad wrote:
         | I've found LLMs to be extremely powerful in research projects.
         | A lot of code related to research is very bespoke by its
         | nature. Using Codex, I've been able to iterate on ideas that I
         | would never had the time or courage to explore before. As for
         | code quality/brevity, it doesn't really matter in this context
         | as long as it works. And it's incredible to have this companion
         | that understands broadly every aspect of tangential knowledge
         | required to execute an idea. I do think it helps that I have
         | over 25 years of experience in my domain (geospatial), which
         | helps me guardrail my interactions and get good results in as
         | few shots as possible.
        
       | dsQTbR7Y5mRHnZv wrote:
       | > in coding, L.L.M.s take away the drudgery and leave the human,
       | soulful parts to you.
       | 
       | I've always hated solving puzzles with my deterministic toolbox,
       | learning along the way and producing something of value at the
       | end.
       | 
       | Glad that's finally over so I can focus on the soulful art of
       | micromanaging chatbots with markdown instead.
        
         | caseyf wrote:
         | +1024. what the FUCK, Anil. We solved coding-is-for-everyone by
         | throwing up our hands. please crush my body under the heaviest
         | layer of abstraction yet and have the llm read my eulogy
         | because who could possibly know me better than the code I spend
         | all day talking to as if it were a human
        
           | someprick wrote:
           | Lurked for >10y here. Created an account just to say, "+1
           | well said."
        
         | rjh29 wrote:
         | The two types of coder argument seems strong to me. Coders who
         | love the art of programming (optimisation for the sake of it,
         | beautiful designs, data structures...) and builders. The former
         | are in for a rough time. The latter are massively enabled and
         | no longer have to worry about smashing together libs by hand to
         | make crud apps.
        
           | swader999 wrote:
           | Yes this is the state of it. But just wait a few months,
           | maybe years, the builders aren't safe either. It just won't
           | be cost effective to let humans build in a matter of time.
        
             | DennisP wrote:
             | Depends on what you mean by "builder."
             | 
             | If you mean "somebody with an idea who wants to make it
             | real" then that person is massively enabled.
        
               | gedy wrote:
               | Those "idea men" I've seen are usually not capable of
               | following through a logical product, even if they start
               | using AI. It's not just the code that's the barrier.
               | 
               | The prototypes or whatever can be handy to help them
               | explain themselves to others of course.
        
               | DennisP wrote:
               | There are plenty of programmers who are perfectly capable
               | of delivering products, who have ideas that are too
               | ambitious to do on their own.
        
               | gedy wrote:
               | Agreed, that's not really who I was referring too.
        
               | stavros wrote:
               | So enabled, in fact, that there's almost no point in
               | downloading an already-made app when you can just
               | trivially tailor-make your own. The builder is massively
               | enabled to quickly make anything they want, for an
               | audience of exactly one.
        
               | DennisP wrote:
               | For tiny apps, sure. Some people are making larger
               | projects that take weeks or months even with AI, that
               | they never could have done otherwise.
        
               | steve-atx-7600 wrote:
               | Strongly disagree. You think you'd be able to prompt your
               | way through creating an app with even half the feature
               | set of Microsoft word, for example? I would be very time
               | consuming to be able to think through how the app should
               | work for many use cases you care about or didn't think
               | about. This time isn't free. Now consider having to do
               | this iteration across many apps you depend on. And, count
               | on introducing regressions when your next prompt is
               | incompatible with existing features. If you are not
               | retired, this is a huge ongoing time sync.
        
               | stavros wrote:
               | You think you were able to prompt your way through
               | creating hello world five years ago? Models improve and
               | they need less and less guidance.
               | 
               | Combined with the fact that my use cases aren't your use
               | cases, yes, it might be cheaper for me to make my own
               | than to slog though software that wasn't built to serve
               | my exact needs.
        
               | steve-atx-7600 wrote:
               | I'm not saying that there's no need for specialty apps
               | optimized for specific use cases or that you can't use
               | llms to create them more cheaply than last year. Only
               | that the time to think through how the app should work
               | and iterate on it is still significant in the way that it
               | was last year if you were given the worlds best team of
               | software engineers and they'd code to your product
               | requirements. You'd only take this path for apps where
               | the time tradeoff is worth it vs "off the shelf" apps.
        
               | stavros wrote:
               | The issue is that off the shelf apps were made at a time
               | when it was too expensive to make apps. Everyone uses 2%
               | of Word, Photoshop, etc, it's just a different 2% for
               | each.
               | 
               | You only need to reimplement that 2% for yourself for it
               | to be worth it, not the entire app.
        
               | GoblinSlayer wrote:
               | How would you address user requests? Tailor-make a custom
               | app for every user?
        
               | stavros wrote:
               | Cars are here and you're wondering how someone could
               | possibly make a faster horse. You wouldn't address user
               | requests. You aren't a business. The users all make their
               | own apps for themselves.
        
               | notpachet wrote:
               | Cars are here and we're all choking on our own
               | atmospheric excrement, so...
        
               | ori_b wrote:
               | Assuming AI lives up to the marketing: Why would someone
               | use an app instead of promoting their agent to figure out
               | how to get something done?
        
             | beepbooptheory wrote:
             | Yall's blood-diamond-ass mommy bots are going to replace
             | bullshit with bullshit and call it a win. The last
             | datacenter will run out of coal and water and we'll be
             | asking: "but _how_ in the world am I going to make this
             | Todo app? "
        
           | crocodile10203 wrote:
           | "bvilders" right now its mostly people who want to build a
           | substandard app and shill it everywhere.
        
           | ori_b wrote:
           | Doordash has also enabled home cooks; they no longer have to
           | worry about smashing together ingredients by hand to make
           | dinner. They just prompt the app to make them the food they
           | want.
           | 
           | Doordash is the future of home cooking.
        
           | falkensmaize wrote:
           | Thinking carefully about the details of implementation
           | MATTERS. Even with crud apps. Getting something "built" fast
           | isn't and should not be the only consideration.
           | 
           | I can go to a junkyard and assemble the parts to build a car.
           | It may run, but for a thousand tiny reasons it will be worse
           | than a car built by a team of designers and engineers who
           | have thought carefully about every aspect of its
           | construction.
        
           | ThrowawayR2 wrote:
           | Imagine if your operating system or compiler were written by
           | the sort of person that thinks " _Coders who love the art of
           | programming ... are in for a rough time._ "
        
         | GoblinSlayer wrote:
         | Why not, normies love to talk with the computer.
        
           | rikroots wrote:
           | Well I do seem to spent a fair amount of my developer time
           | swearing at my laptop screen. And then there's that time I
           | spend just prior to writing code just staring at the wall
           | while I figure out what sort of code I want to write - if I
           | can repackage that wall-staring time into "time spent
           | consulting with AI about approaches and architecture
           | decisions" I'm sure my engineering manager will think more
           | kindly of me ...
        
             | GoblinSlayer wrote:
             | I'm puzzled why they don't speak aloud. Isn't it more
             | natural AI interface? How difficult it is to connect a
             | microphone to speech to text engine and connect that to AI?
             | And then speak aloud. Your manager will be happy to hear
             | you work.
        
               | throwaway27448 wrote:
               | It's easier to fake humanity through toneless text with
               | narrow context and low expectstions, I think. A chatbot
               | you type to is of course going to impress easier
        
         | IanCal wrote:
         | To read it in a kinder way, I can focus on a complex logic
         | problem, a flow, an architecture or micro optimisation. I can
         | have an llm setup the test harnesses.
         | 
         | I improved test speed which was fun, I had an llm write a nice
         | analysis front end to the test timing which would have taken
         | time but just wasn't interesting or hard.
         | 
         | Ask yourself if there are tasks you have to do which you would
         | rather just have done? You'd install a package if it existed or
         | hand off the work to a junior if that process was easy enough,
         | that kind of thing. Those are places you could probably use an
         | LLM.
        
           | bluefirebrand wrote:
           | > Ask yourself if there are tasks you have to do which you
           | would rather just have done?
           | 
           | Yeah. My laundry, my dishes, my cooking...
           | 
           | You know. Chores.
           | 
           | Not my software, I actually _enjoy_ building that
        
             | DennisP wrote:
             | I enjoy solving interesting problems in software. But when
             | I was doing it for a living, the majority of my work was
             | pretty tedious. I'd have been thrilled to turn over that
             | part to AI and spend all my time doing the interesting
             | stuff.
        
               | bluefirebrand wrote:
               | This is a fools errand
               | 
               | We are paid to do the tedious stuff _because_ it is
               | tedious. If we actually ever succeed in automating away
               | the tedious stuff, we 're out of work
        
               | DennisP wrote:
               | There definitely is economic value in solving the more
               | challenging problems. Junior devs who can only do the
               | tedious parts have lower salaries.
        
               | bluefirebrand wrote:
               | There are way fewer challenging problems that people are
               | willing to pay me to solve.
               | 
               | Sure I would love to be working on some cutting edge
               | challenging stuff, but the reality is it has been much
               | more realistic to do the tedious stuff for pay instead
        
               | kjkjadksj wrote:
               | You think people are still getting senior level comp when
               | the job is prompting llm? Ha!
        
               | sph wrote:
               | Don't you get it? Machine do the tedious work, all we get
               | to do now is the fun part and we can just relax the rest
               | of the day.
               | 
               | I am producing 5x as before, my boss is paying me the
               | same salary just for two hours of actual work per day. I
               | have so much more time to pursue my passions.
               | 
               | Isn't the future great?
        
               | bluefirebrand wrote:
               | > I am producing 5x as before, my boss is paying me the
               | same salary just for two hours of actual work per day
               | 
               | I don't believe any of this
        
               | Ygg2 wrote:
               | > I am producing 5x as before, my boss is paying me the
               | same salary just for two hours of actual work per day.
               | 
               | Great. Once your boss notices your actual work has
               | decreased, he'll adjust compensation, increase workload,
               | or both.
        
               | apsurd wrote:
               | You forgot the /s at the end.
               | 
               | Can't imagine you really think "the market forces" all
               | point toward a utopia for the _workers_? We 're all just
               | gonna get paid for 2 hours of work a day and post pics
               | from the beach with a special shout-out to Claude?
        
               | DennisP wrote:
               | I'm surprised you've had three replies so far that didn't
               | notice your sarcasm.
               | 
               | But we've been automating the tedious work since the
               | 1950s. There were probably devs back then complaining
               | about imminent job loss when the first compilers were
               | invented. Maybe some jobs _were_ lost, temporarily, but
               | ultimately we all got more ambitious about what software
               | we could make. We ended up hiring more programmers and
               | paying them better, because each one provided so much
               | more value.
               | 
               | When the machines are able to do the hard stuff better
               | than humans, that's when we'll really be in trouble.
        
               | sph wrote:
               | I do not believe that past performance is a guarantee of
               | future results. The era of well paid programmers in great
               | demand is pretty much over, and it's not only because of
               | AI. Even if machines are dumb enough they require
               | supervision, the big bosses do not care and will always
               | prefer the dumb machine if it saves them money vs hiring
               | a junior dev. It means the poor sods that supervise these
               | machines will have to work harder to keep up with demand.
        
               | DennisP wrote:
               | Maybe that'll happen one day, but it hasn't so far. As of
               | this month, Glassdoor reports the median total pay for
               | software developers across all industries and experience
               | levels as $149K.
               | 
               | https://www.glassdoor.com/Salaries/software-engineer-
               | salary-...
        
               | satvikpendem wrote:
               | This but unironically. We're at a point where there is
               | still a gap between what managers expect and how fast AI
               | can work. I genuinely do have days where I finish a few
               | tickets and I'm done.
        
             | apsurd wrote:
             | interesting comparison to cooking. cooking is a chore and
             | takes effort and people enjoy cooking.
        
               | bluefirebrand wrote:
               | Eating is also not really optional
               | 
               | If you're going to spend a pretty good chunk of your
               | lifetime eating, you might as well get good at it so you
               | can enjoy the food you make
        
               | IanCal wrote:
               | Do you want to eat good food or make good food? Is doing
               | the dishes something you hand to a machine or do you
               | always do it by hand? Are there any ingredients you buy
               | pre-made (pesto, curry pastes, do you make your own panko
               | breadcrumbs)?
        
             | _aavaa_ wrote:
             | You can enjoy doing woodworking without power tools but
             | that's irrelevant to a job where people want it done fast
             | with power tools.
        
               | wsve wrote:
               | Woodworking analogy for AI is not "power tools vs
               | handsaw", its "power tools vs. wood 3D printer". You
               | don't do any of the creating, you only ideate and allow
               | the machine to do all the creating. It's simply not wood
               | working anymore. Its something else entirely
        
               | IanCal wrote:
               | You don't have to choose between entirely hand coded and
               | entirely AI built code.
        
               | paradox460 wrote:
               | A friend was recently redoing his kitchen. They hired a
               | carpenter for cabinetry, and his wife asked him if he
               | would be willing to make it with only hand tools.
               | 
               | Carpenter told her he'd be happy to, it would take 8
               | weeks longer, cost more, and probably wouldn't look any
               | better than the regular way
        
             | IanCal wrote:
             | Absolutely everything about it in equal measure? You live
             | environment config, setting up test harnesses, coding the
             | complex part all identically the same? Nothing you would
             | hand off?
             | 
             | Do you find there are zero chores in software development
             | and everything is an identical delight?
        
           | relativeadv wrote:
           | But you don't actually do any of that, do you? Instead, you
           | get tired and lazy and attempt to have the LLM solve those
           | hard problems for you too. You just don't tell others about
           | it.
        
             | DennisP wrote:
             | What an odd bit of moralizing. GP said they enjoy doing the
             | hard parts, in which case they probably do them, because
             | it's fun. If they actually don't enjoy it, there's nothing
             | wrong with them using the LLM, when it's up to the task,
             | and then just checking to make sure the code is good.
        
         | crocodile10203 wrote:
         | I mean if > 30% of my work is drudgery, I have failed already.
        
         | arcxi wrote:
         | amidst this whole AI craze it's illuminating to learn how many
         | programmers secretly hated programming all along
        
           | sph wrote:
           | It's clear at this point that the term programmer was used to
           | refer to two very different types of people.
        
           | doug_durham wrote:
           | I don't know if it's "hate" rather than "a means to an ends".
           | I love learning new languages, and coding. But it was always
           | a means to an ends. The dopamine hit always came from seeing
           | the project compile and do something.
        
             | m0llusk wrote:
             | There are multiple ends in conflict. Code skillfully
             | constructed using abstractions that fit well to the problem
             | space can be extended, maintained, and refactored as
             | necessary to serve customers and markets from high to low
             | level over long periods of time with all the social and
             | industrial change that comes with that. Simply putting in
             | place mechanisms that deliver what is needed now end up
             | unintentionally cutting off future variants, alternative
             | uses, longevity, and robustness all to minimize perceived
             | costs.
             | 
             | And it isn't so much that one approach may be better than
             | another. That is going to depend on context and available
             | resources and more. What we are seeing is the short term
             | being served to the absolute exclusion of thought about the
             | longer term. Maybe if that goes fast and well enough then
             | it will be sufficient, but churning out code bases that
             | endure is a challenge that is only starting to be tested.
        
             | polishdude20 wrote:
             | Yeah and especially the satisfaction that you were able to
             | make a user delighted to use your thing. Fixing bugs,
             | making things faster, adding new features, for me
             | personally I do it because I feels really good when a
             | customer loves to use the thing I've built.
             | 
             | Weather I've done the manual coding work myself or have
             | prompted an LLM to cause these things to happen, I still
             | chose what to work on and if it was worthy of the users'
             | time.
        
           | wsve wrote:
           | This is exactly how I feel. I knew it already to an extent
           | from my time in college, but so many people come into this
           | industry because they want to be able to produce the end
           | product, or just have a stable job that makes good money.
           | Neither of those are bad reasons to get into this profession,
           | but it does make me sad how few peers I have who do
           | programming because they're passionate about the act of
           | programming. The problem solving, the dance of using
           | programming languages to communicate efficiently and robustly
           | to both machines and humans... I'm very sad how
           | enthusiastically so many of my peers just toss that away.
        
           | paradox460 wrote:
           | I think a lot of us like solving novel problems. But the
           | menial drudgery of most modern software, where you're writing
           | code in an app that was written in a week 8 years ago and
           | then had mountains of "get it done quickly and we can improve
           | it later" over the years, wears on everyone. Much as the
           | advent of decent cordless tools revolutionized "workman"
           | trades, ai helps programmers
        
         | barnabee wrote:
         | I like designing data, algorithms, and systems. I like picking
         | the right tools for the job. I like making architectural and
         | user interface (CLI, configuration format, GUI, whatever)
         | decisions.
         | 
         | Actually typing code is pretty dull. To the extent that I
         | rarely do it full time (basically only when prototyping or
         | making very simple scripts etc.), even though I love making
         | things.
         | 
         | So for me, personally, LLMs are great. I'm making more software
         | (and hardware) than ever, mostly just to scratch an itch.
         | 
         | Those people that really love it should be fine. Hobbies aren't
         | supposed to make you money anyway.
         | 
         | I don't have much interest in maintaining the existence of
         | software development/engineering (or anything else) as a
         | profession if it turns out it's not necessary. Not that I think
         | that's really what's happening. Software engineering will
         | continue as a profession. Many developers have been doing
         | barely useful glue work (often as a result of
         | bad/overcomplicated abstractions and tooling in the first
         | place, IMO) and perhaps _that_ won 't be needed, but plenty
         | more engineers will continue to design and build things just
         | more effectively and with better tools.
        
           | staplers wrote:
           | The assembly line has been mass producing ready-made products
           | for over 100 years and yet product quality, material
           | stability, aesthetic trends, and function design still
           | dominate the purchasing decisions of the general public.
           | 
           | Being tapped into fickle human preference and changing
           | utility landscape will be necessary for a long time still. It
           | may get faster and easier to build, but tastemakers and
           | craftsmen still have heavy sway over markets than can mass-
           | produce vanilla products.
        
             | Ygg2 wrote:
             | > The assembly line has been mass producing ready-made
             | products for over 100 years and yet product quality,
             | material stability
             | 
             | Luckily if you want stability or quality they are nowhere
             | to be found.
        
               | dmd wrote:
               | I would generally put "stability" and "quality" as
               | attributes of mass production far more than that of
               | handmade things. Yes, an expert can make a quality
               | product by hand, but MOST handmade things are far more
               | likely to be shoddy. The whole point of mass production
               | was that suddenly you could make a million identical
               | perfect products.
        
               | Ygg2 wrote:
               | True, but motivations for mass production also are
               | motivations for making things worse off overall.
        
             | barnabee wrote:
             | Agree with this. I think LLMs allow more time to bring
             | these things to the fore and more leverage to do them cost
             | efficiently.
        
           | galactus wrote:
           | I think reducing what LLMs do to << typing >> is misleading.
           | If it was just typing, you could simply use speech-to-text.
           | But LLMs do far more than that, they shape the code itself.
           | And I think we lose something when we delegate that work to
           | LLMs
        
             | jodleif wrote:
             | Agreed. Also, it takes time to understand a domain
             | properly- so the innate slowness of coding helps with
             | letting things "simmer" in the back of the mind.
        
             | sieste wrote:
             | The art is to decide when shaping the code yourself is
             | worth your time. Not only financially but also experience
             | gain and job satisfaction.
        
             | barnabee wrote:
             | It's not that they replace the act of typing, so much as
             | figuring out how to express the specific algorithm or data
             | structure in a given programming language, typing _that_ ,
             | debugging it, etc.
             | 
             | Once I can describe something well, that's most of the
             | interesting part (to me) done.
        
             | AStrangeMorrow wrote:
             | We do lose something, but really I still see it as an
             | extension of autocomplete.
             | 
             | I had some pieces of code I wrote I was quite proud of:
             | well documented, clear code yet clever designs and
             | algorithm.
             | 
             | But really what always mattered most to me was designing
             | the solution. Then the coding part, even though I take some
             | pride in the code I write, was most a mean to an end.
             | Especially once I start having to add things like data
             | validation and API layers, plotting analysis results and so
             | many other things that are time consuming but easy and imho
             | not very rewarding
        
         | GorbachevyChase wrote:
         | You can always code by hand as a hobby.
         | 
         | If someone is paying you for your work results, that you find
         | it interesting or fun is orthogonal. I get the sense from the
         | commentary section here that there's a perception that writing
         | programs is an exceptional profession where developer happiness
         | is an end unto itself, and everyone doing it deserves to be a
         | millionaire in the process. It just comes across as child-like
         | thinking. I don't think many of us spend time, wondering if the
         | welder enjoys the torch or if a cheaper shop weld is robbing
         | the human welder of the satisfaction of a field weld. And we
         | don't shed so much ink wondering if digital spreadsheets are a
         | moral good or not because perhaps they robbed the accountant of
         | the satisfaction of holding a beautiful quill in hand dipped
         | expertly in carefully selected ink. You're lucky if you enjoy
         | your job, I think most of us find a way to learn to enjoy our
         | work or at least tolerate it.
         | 
         | I just wish all the moaning would end. Code generation is not
         | new, and that the state of the art is now as good at
         | translating high-level instructions into a program at least as
         | well as the bottom 10% of programmers is a huge win for
         | humanity. Work that could be trivially automated, but is not
         | only because of the scarcity of programming knowledge is going
         | to start disappearing. I think the value creation is going to
         | be tremendous and I think it will take years for it to
         | penetrate existing workflows and for us to recognize the value.
        
           | notpachet wrote:
           | > at least as well as the bottom 10% of programmers
           | 
           | I don't think this is the flex you think it is... in my
           | experience, the bottom 10% of programmers are actively
           | harmful and should never be allowed near your codebase.
        
             | GorbachevyChase wrote:
             | Quite a few people think that about Claude code. I disagree
             | with them, personally, but I think we can agree that AI
             | code generation is qualitatively at least as good as the
             | worst human professionals. I think we would also probably
             | agree that the state of the art today is not as good as the
             | very best.
             | 
             | The value per dollar spent is a different calculus and I
             | would say that state of the art models completely surpass
             | any individual's productive output.
        
           | apsurd wrote:
           | > And we don't shed so much ink wondering if digital
           | spreadsheets are a moral good or not because perhaps they
           | robbed the accountant...
           | 
           | Caught my eye. I _do_ think we should wonder and hold
           | intentionality around products, especially digital products,
           | like the spreadsheet. Software _is_ different. It 's a
           | limitless resource with limitless instantaneous reach. A good
           | weld is beautiful in its own right, but it's not that.
           | 
           | The spreadsheet in particular changed the way millions of
           | people work. Is it more productive? Is an army of middle-
           | managers orienting humanity through the lens of a literal
           | 2x2cm square a net good?
           | 
           | I say we should moralize on that.
        
           | whateveracct wrote:
           | since when has velocity or volume of codegen been the
           | bottleneck for any business?
           | 
           | i write less code than my AI-using coworkers but I have as
           | much or more impact. Coding wasn't so hard that I need to
           | spend time learning a new proprietary tech stack with a
           | subscription fee lol. I believe plenty of engineers did suck
           | enough and computers to benefit tho. That is where Anthropic
           | makes their money.
        
         | RobRivera wrote:
         | Yea! Back to my amazing Pax Americana of friendly neighbors,
         | high trust in my authorities, and cheerful joyous days in oeace
         | and harmony with my fellow man, complete with gum drop smiles
         | and firm faith in my institutions. A truly brave new world
        
         | InfamousRece wrote:
         | I'd love to outsource all the boring, tedious parts of my job
         | to LLM. Unfortunately it is the upper management who decide
         | which parts of my job are boring.
        
       | 0xbadcafebee wrote:
       | Back in the day, programming was done on punch cards. In 20
       | years, that's how kids will see typing out lines of program code
       | by hand.
        
         | Revanche1367 wrote:
         | At the rate things have been going, that is likely to happen in
         | 20 days rather than 20 years.
        
         | znort_ wrote:
         | different things. adding levels of abstraction is not the same
         | as having a statistical model generate abstractions for you.
         | 
         | you can still call it spec-programming but if you don't audit
         | your generated code then you're simply doing it wrong; you just
         | don't realize that yet because you've been getting away with it
         | until now.
        
       | yubainu wrote:
       | In the near future, a "good programmer" might not be defined by
       | someone who can write bug-free, clear code, but rather by someone
       | who can prompt for code that works consistently within the
       | context of AI. If that happens, I'll have to find a different
       | job.
        
         | shinycode wrote:
         | That's the exact definition our CEO gave of our job this week.
         | That's how he sees and expects us to work now. I feel some
         | anxiety because that's too much too fast. We went from << we
         | need to fix every single bug we encounter >> to << it doesn't
         | matter if there's bugs as long as we ship a feature fast >>
        
         | olsondv wrote:
         | At least at my company, we have never really cared how it gets
         | done, even before AI. It just has to work (ideally bug-free and
         | maintainable) by the deadline. If you can keep up with shorter
         | deadlines, more power to you. It's basically a modern John
         | Henry vs the steam drill.
        
       | nenadg wrote:
       | sensationalism give it a couple of months
        
       | allreduce wrote:
       | I'm starting to find the naive techno-optimism here annoying. If
       | you don't have capital or can do something else you will be
       | homeless.
        
         | ipnon wrote:
         | But you only $200/month for the productivity of what used to
         | cost monthly salary for 10 software engineers. Doesn't this
         | democratize software construction?
        
           | allreduce wrote:
           | It commoditizes software construction.
           | 
           | The resources to learn how to construct software are already
           | free. However learning requires effort, which made learning
           | to build software an opportunity to climb the ladder and
           | build a better life through skill. This is democratization.
           | 
           | Now the skill needed to build software is starting to
           | approach zero. However as you say you can throw money at an
           | AI corporation to get some amount of software built. So the
           | differentiator is capital, which can buy software rather
           | cheaply. The dependency on skill is lessened greatly and
           | software is becoming worthless, so another avenue to escape
           | poverty through skill closes.
        
           | kjkjadksj wrote:
           | Did ms word usher in a surge of novel writing? Not really
           | apparent.
        
         | gf000 wrote:
         | Well, there are so many more lower hanging fruits that LLMs can
         | actually replace before they get to developers -- basically
         | every middle manager, and a significant chunk of all white
         | collar jobs.
         | 
         | I'm not convinced software developers will be replaced -
         | probably less will be needed and the exact work will be
         | transformed a bit, but an expert human still has to be in the
         | loop, otherwise all you get is a bunch of nonsense.
         | 
         | Nonetheless, it may very well transform society and we will
         | have to adapt to it.
        
           | allreduce wrote:
           | Not all software development will be automated immediatly.
           | But I've noticed that many skills I've built are lessened in
           | worth with every model release.
           | 
           | Having a lot of specifics about a programming environment
           | memorized for example used to be the difference between
           | building something in a few hours and a week, but now is
           | pretty unimportant. Same with being able to do some quick
           | data wrangling on the command line. LLMs are also good at
           | parsing a lot of code or even binary format quickly and
           | explaining how it works. That used to be a skill. Knowing a
           | toolbox of technologies to use is needed less. Et cetera.
           | 
           | They haven't come for the meat of what makes a good engineer
           | yet. For example, the systems-level interfacing with external
           | needs and solving those pragmatically is still hard. But the
           | tide is rising.
        
             | samiv wrote:
             | The capitalists and industrialists have waited for
             | centuries to get rid of paid labor. Imagine the profits
             | once the cost of human work gets out of the loop!
             | 
             | Of course the question that is left unanswered is how the
             | economy will work there's no one left with purchasing
             | power. But I guess the answer to this is, the same way it
             | works now in any developing country without much of a
             | middle class.
        
           | hnthrow0287345 wrote:
           | >I'm not convinced software developers will be replaced
           | 
           | Most of us will probably need to shift to security. While you
           | can probably build AI specifically to make things more
           | secure, that implies it could also attack things as well, so
           | it ends up being a cat-and-mouse game that adjusts to what
           | options are available.
        
           | olsondv wrote:
           | I don't see middle managers taking the initial brunt unless
           | they truly are just pushing papers around. At companies of
           | sufficient size, they do play a role of separation between C
           | suite and the grunts. To me, certain low-performing grunts
           | will be the first out. Then a team reorg to rebalance. Then
           | some middle managers will be out as fewer of them can handle
           | multiple teams.
        
           | j-a-a-p wrote:
           | Agree. Marketing, Finance, Legal, already having huge impact
           | for junior positions.
        
           | GeoAtreides wrote:
           | you know, natural attrition is still attrition.
        
           | flux3125 wrote:
           | > probably less will be needed and the exact work will be
           | transformed a bit
           | 
           | My guess is the opposite: they'll throw 5-10x more work at
           | developers and expect 10x more output, while the marginal
           | cost is basically just a Claude subscription per dev.
        
         | butILoveLife wrote:
         | Yep. I own a software shop and yesterday was when I realized
         | that I'm no longer going to be a 1%er doing this.
        
           | dominotw wrote:
           | what happened yesterday?
        
         | 0x262d wrote:
         | A lot of people expect to be owning the capital. However I also
         | just don't think the technology will displace programmers that
         | quickly.
        
       | CrzyLngPwd wrote:
       | Visual Basic was the end of programming as we knew it...until it
       | wasn't.
        
         | heikkilevanto wrote:
         | And before that, COBOL was supposed to allow computer users to
         | write in almost plain English without even knowing the machine
         | instruction set.
         | 
         | It did change the programming landscape, but there was still a
         | huge need for this new kind of programmers.
        
       | Nevermark wrote:
       | The psycho engineering of model prompts does feel very Phillip K.
       | Dick.
       | 
       | If your base prompt informs the model they are a human software
       | developer in a Severed situation, it gets even closer.
        
       | suheilaaita wrote:
       | I'm from an accounting/finance background and spent about 10
       | years in Big4. I was always into tech, but never software
       | development because writing code (as I thought) takes years to
       | master, and I had already chosen accounting.
       | 
       | Fast forward to 2024 when I saw Cursor (the IDE coding agent
       | tool). I immediately felt like this was going to be the way for
       | someone like me.
       | 
       | Back then, it was brutal. I'd fight with the models for 15
       | prompts just to get a website working without errors on
       | localhost, let alone QA it. None of the plan modes or
       | orchestration features existed. I had to hack around context
       | engineering, memories, all that stuff. Things broke constantly.
       | 10 failures for 1 success. But it was fun. To top it all off,
       | most of the terminology sounded like science fiction, but it got
       | better in time. I basically used AI itself to hack my way into
       | understanding how things worked.
       | 
       | Fast forward again (only ~2 years later). The AI not only builds
       | the app, it builds the website, the marketing, full
       | documentation, GIFs, videos, content, screen recordings. It even
       | hosts it online (literally controls the browser and configures
       | everything). Letting the agent control the browser and the
       | tooling around that is really, genuinely, just mad science
       | fiction type magic stuff. It's unbelievable how often these
       | models get something mostly right.
       | 
       | The reality though is that it still takes time. Time to
       | understand what works well and what works better. Which agent is
       | good for building apps, which one is good for frontend design,
       | which one is good for research. Which tools are free, paid,
       | credit-based, API-based. It all matters if you want to control
       | costs and just get better outputs.
       | 
       | Do you use Gemini for a website skeleton? Claude for code? Grok
       | for research? Gemini Deep Search? ChatGPT Search? Both? When do
       | you use plan mode vs just prompting? Is GPT-5.x better here or
       | Claude Opus? Or maybe Gemini actually is.
       | 
       | My point is: while anyone can start prompting an agent, it still
       | takes a lot of trial and error to develop intuition about how to
       | use them well. And even then everything you learn is probably
       | outdated today because the space changes constantly.
       | 
       | I'm sure there are people using AI 100x better than I am. But
       | it's still insane that someone with no coding background can
       | build production-grade things that actually work.
       | 
       | The one-person company feels inevitable.
       | 
       | I'm curious how software engineers think about this today. Are
       | you still writing most of your code manually?
        
         | butILoveLife wrote:
         | > it still takes a lot of trial and error to develop intuition
         | about how to use them well.
         | 
         | I used to think so. Then a customer made their own replacement
         | for $600/mo software in 2 days. The guy was a marketer by
         | training. I don't exaggerate. I saw it did the exact same
         | things.
        
           | shinycode wrote:
           | It's true there's some magic effect from Claude code's work.
           | But still, often it's not exactly the same infra and scaling
           | than production grade. But for a customer I guess that's
           | perfect, they have a mean to make their own tools instead of
           | relying on platforms to build those tools.
        
             | suheilaaita wrote:
             | I Agree on the customer empowerment point.
             | 
             | I'd push back slightly on the production grade point. The
             | models aren't the ceiling, the user's mental model of
             | software is, depending on his experience/knowledge.
             | 
             | Someone just starting out will get working prototypes and
             | solid MVPs, which is genuinely impressive. But as they
             | develop real engineering intuition -- how Git works, how
             | databases behave under load, how hosting and infra fit
             | together -- that's when they start shipping production-
             | grade things with Claude Code.
             | 
             | Based on what I'm seeing, the tool can handle it. The
             | question is whether the person behind it understands what
             | they're asking for. Anthropic, for example, mostly uses
             | claude code to develop claude code.
        
           | suheilaaita wrote:
           | It's true. We're also at the point where the models and the
           | orchestration around them are so good that any beginner to
           | those tools who knows how to use a computer can build working
           | apps. Interesting times.
           | 
           | I was pointing out that practice helps with the speed and the
           | scope of capabilities. Building a personal prototype is a
           | different ballgame than building a production solution that
           | others will use.
        
             | butILoveLife wrote:
             | I said this 4 weeks ago...
             | 
             | Buddy its outdated.
        
           | shimman wrote:
           | Can you say what kind of software the customer replaced?
        
       | holoduke wrote:
       | The best developers are the ones using AI to its best. Mediocre
       | devs will become a useless skill as even a PO could become one.
       | But one who understands architecture, software, code and AI will
       | be expensive to hire. I know plenty of them. I wory for the ones
       | not willing to adopt ai.
        
       | somewhereoutth wrote:
       | I have a suspicion that for a task (or to make an artifact) of a
       | given complexity, there is a minimum level of human engagement
       | required to complete it successfully - and that human engagement
       | cannot be substituted for anything else. However, the actual
       | human engagement for a task is not bounded above - efficiency is
       | often less (much less?) than 100%.
       | 
       | So tools (like AI) can move us closer to the 100% efficiency (or
       | indeed further away if they are bad tools!) but there will always
       | be the residual human engagement required - but perhaps moved to
       | different activities (e.g. reviewing instead of writing).
       | 
       | Probably very effective teams/individuals were already close to
       | 100% efficiency, so AI won't make much difference to them.
        
       | d4rkp4ttern wrote:
       | I see lots of discussions about humans no longer writing code but
       | the elephant in the room is the rapid extinction of human-review
       | of AI-made code. I expect this will lead to a massive hangover.
       | In the meantime we try to mitigate this by ensuring the structure
       | of code remains AI-friendly. I also expect some new types of
       | tools to emerge that will help with this "cognitive debt".
        
         | olsondv wrote:
         | That is why I do not use the multi agent team technique. My
         | code generation has atrophied, but my code review skills have
         | only gotten stronger both for human and AI code. If I handed
         | over both, it hurts my employability and will definitely lead
         | to that hangover.
        
         | kusokurae wrote:
         | My impression is that people who think that LLMs will
         | completely release reviewing or writing code have never really
         | worked on anything safety critical. I'm not looking forward to
         | the next wave of pacemaker glitches.
        
           | kjkjadksj wrote:
           | You act like we live in a world where companies are held
           | sufficiently liable.
        
       | whoisstan wrote:
       | I feel the need to tell the LLM to rewrite the article for a
       | software developer audience, but don't, those kinds of passage
       | are hard to overcome:
       | 
       | 'Salva opened up his code editor -- essentially a word processor
       | for writing code -- to show me what it's like to work alongside
       | Gemini, Google's L.L.M. '
       | 
       | And what's up with L.L.M, A.I., C.L.I. :)
        
         | moregrist wrote:
         | > And what's up with L.L.M, A.I., C.L.I. :)
         | 
         | It's probably N.Y.T. style requirements; a lot of style guides
         | (eg: Chicago Manual of Style, Strunk & White, etc) have a
         | standard form for abbreviations and acronyms. A paper like
         | N.Y.T. does too and probably still employs copy editors who
         | ensure that every article conforms to it.
        
       | __mharrison__ wrote:
       | I wasn't around when we moved to that stack from assembly. I
       | didn't experience the mourning then.
       | 
       | Most folks I hang out with are infatuated with turning tokens
       | into code. They are generally very senior 15+ years of
       | experience.
       | 
       | Most folks I hang out with experience existential dread for
       | juniors and those coming up in the field who won't necessarily
       | have the battle scars to orchestrate systems that will work in
       | the will world.
       | 
       | Was talking with one fellow yesterday (at an AI meetup) who says
       | he has 6 folks under him, but that he could now run the team with
       | just two of them and the others are basically a time suck.
        
       | DGAP wrote:
       | Lots of cope here. Highly paid white collar jobs are going to
       | disappear.
        
       | youknownothing wrote:
       | I once suggested a drinking game: shot every time someone says "X
       | is dead". I was told to f** off because I'd kill half of
       | humanity.
       | 
       | COBOL is dead. Java is dead. Programming is dead. AI is dead
       | (yes, some people are already claiming this:
       | https://hexa.club/@phooky/116087924952627103)
       | 
       | I must be the kid from The Sixth Sense because I keep seeing all
       | these allegedly dead guys around me.
        
       | dorfsmay wrote:
       | For me, the biggest shift is people who don't care about local
       | AI. The idea that you can no longer code without paying a tax to
       | one of the billion $ backed company isn't sitting well.
        
         | hacker_homie wrote:
         | Yeah look at the price of netfilx, do you think starting at
         | $200 it's going to stay anywhere close to that.
        
           | dorfsmay wrote:
           | The price does not matter, even if it were free. If you need
           | to be logged on into an external service to be able to code,
           | it's just not the same any more, and I'm thinking of basic
           | technology here, but the political/distopian ramifications
           | are crazy.
        
             | duskdozer wrote:
             | >From: noreply@openai.com >Subject: Your account has been
             | terminated for violating the Terms of Service
             | 
             | People have various online accounts locked or deleted for
             | no given reason all the time. Just get the right person to
             | say the word, and you're out.
        
         | glaslong wrote:
         | The marginal differences in quality seem pretty meaningful
         | right now, enough to make Claude wildly dominant, but some of
         | the locally runnable models like Qwen feel only a few months
         | behind the leaders.
         | 
         | I'm betting the generational gains level off and smaller local
         | models close the gap somewhat. Then harnesses will generally be
         | more important than model, and proprietary harnesses will not
         | offer much more than optimization for specific models. All
         | while SaaS prices ratchet up, pushing folks toward local and
         | OSS. Or at least local vs a plethora of hosted competition,
         | same as cloud vs on prem.
        
         | FuckButtons wrote:
         | I don't understand why more people aren't focused on how to get
         | the benefits of ai but on your own machine. If the last 20
         | years of software transitioning off of our desktops and into
         | the cloud has taught us anything, it's that letting corporate
         | entities run the software you rely on end to end gives you:
         | worse software with more bugs, surveillance and subscriptions.
         | Why on earth would you want that for _everything you do_.
        
           | whiplash451 wrote:
           | Local AI is what people want/need, but centralized AI is
           | where the investors' money is flowing, because a walled
           | garden has always been easier to turn into a cash printer.
        
         | timcobb wrote:
         | This is the only problem but hopefully we'll be able to fix
         | this issue, otherwise yikes we are doooomed.
        
       | flux3125 wrote:
       | > You can't just tell an agent, Build me the code for a
       | successful start-up. The agents work best when they're being
       | asked to perform one step at a time
       | 
       | That's also true for humans. If you sit down with an LLM and take
       | the time to understand the problem you're trying to solve, it can
       | perfectly guide you through it step by step. Even a non-technical
       | person could build surprisingly solid software if, instead of
       | immediately asking for new shiny features, they first ask
       | questions, explore trade-offs, and get the model's opinion on
       | design decisions..
       | 
       | LLMs are powerful tools in the hands of people who know they
       | don't know everything. But in the hands of people who think they
       | always know the best way, they can be much less useful (I'd say
       | even dangerous)
        
         | GorbachevyChase wrote:
         | I appreciate this sober take. If you hired a remote developer
         | and the only thing you said to that person was "build a program
         | that does this. Make no mistakes" would you expect that to be
         | successful? Are you certain you would get what you wanted?
        
           | AstroBen wrote:
           | Any competent developer there is going to push back and get
           | the needed information out of you.
           | 
           | LLMs don't know when you're under-specifying the problem.
        
             | GorbachevyChase wrote:
             | That's interesting because that is one feature of Claude
             | code that I like. Given an overly broad problem statement.
             | It does go into a planning loop where it seeks clarifying
             | questions. I think this probably has something more to do
             | with the harness than the model, but you see what I mean.
             | From a user perspective that distinction doesn't really
             | matter.
        
       | bwhiting2356 wrote:
       | > Pushing code that fails pytest is unacceptable and
       | embarrassing.
       | 
       | CI is for preventing regressions. Agents.md is for avoiding
       | wasted CI cycles.
        
       | anonzzzies wrote:
       | I dunno; I finally can focus on writing the logic I wanted to
       | write all along and finally my upbringing in formal verification
       | makes sense as I can spend my time on it instead of figuring what
       | garbage (I cannot use it in my work but sbcl is one of the things
       | that does not grow tumors in software) updates I will never ever
       | need my friends added to the framework or language or ide I
       | happen to use.
        
       | cineticdaffodil wrote:
       | Revenge of the writers and software managers, the wishfull hoping
       | for hurt of those made redundant upon those they blame for having
       | been made redundant.
        
       | daveguy wrote:
       | > "...melodramatic prose might seem kind of nuts, but as their
       | name implies, large language models are language machines.
       | "Embarrassing" probably imparted a sense of urgency.
       | 
       | > "If you say, This is a national security imperative, you need
       | to write this test, there is a sense of just raising the stakes,"
       | Ebert said.
       | 
       | I'm not sure why programmers and science writers are still
       | attributing emotions to this and why it works. Behind the LLM is
       | a layer that attributes attention to various parts of the
       | context. There are words in the English language that command
       | greater attention. There is no emotion or internal motivation on
       | the part of the LLM. If you use charged words you get charged
       | attention. Quite literally "attention is all you need" to
       | describe why appealing to "emotion" works. It's a first order
       | approximation for attention.
        
       | nativeit wrote:
       | So you've vibe coded an app. That's just swell. You want to
       | release it? Don't. You can't support it. You can't update it. You
       | are one bad prompt away from it collapsing.
       | 
       | We are convincing a generation of morons that they can do
       | something they plainly cannot. This will be a major problem, and
       | soon.
        
       ___________________________________________________________________
       (page generated 2026-03-14 23:01 UTC)