[HN Gopher] AI Coding assistants provide little value because a ...
       ___________________________________________________________________
        
       AI Coding assistants provide little value because a programmer's
       job is to think
        
       Author : d0liver
       Score  : 71 points
       Date   : 2025-04-27 20:51 UTC (2 hours ago)
        
 (HTM) web link (www.doliver.org)
 (TXT) w3m dump (www.doliver.org)
        
       | fire_lake wrote:
       | Most developers use languages that lack expressivity. LLMs allow
       | them to generate the text faster, bringing it closer to the speed
       | of thought.
        
       | bamboozled wrote:
       | What if they help you to think ?
       | 
       | I know LLMs are masters of averages and I use that to my
       | advantage.
        
       | 65 wrote:
       | I wish people would realize you can replace pretty much any LLM
       | with GitHub code search. It's a far better way to get example
       | code than anything I've used.
        
       | monkaiju wrote:
       | Couldn't agree more. And I'm regards to some of the comments
       | here, generating the text isn't the hard OR time consuming part
       | of development, and that's even assuming the generated code was
       | immediately trustworthy. Given that it isn't must be checked,
       | it's really just not very valuable
        
       | lobochrome wrote:
       | Object-oriented languages provide little value because a
       | programmer's job is to think
       | 
       | Memory-safe languages provide little value because a programmer's
       | job is to think
       | 
       | ...
        
         | DidYaWipe wrote:
         | Not comparable at all.
        
         | ahartmetz wrote:
         | Now this isn't a killer argument, but your examples are about
         | readability and safety, respectively - the quality of the
         | result. LLMs seem to be more about shoveling the same or worse
         | crap faster.
        
           | dymk wrote:
           | Have you tried an AI coding assistant, or is that just the
           | impression you get?
        
         | skydhash wrote:
         | Using deterministic methods as counter arguments about a
         | probabilistic one. Something apples, something oranges....
        
       | protocolture wrote:
       | So theres no value in dealing with the repeatable stuff to free
       | the programmer up to solve new problems? Seems like a stretch.
        
         | 9rx wrote:
         | There is no new value that we didn't already recognize. We've
         | know for many decades that programming languages can help
         | programmers.
        
       | adocomplete wrote:
       | I disagree. It's all about how you're using them. AI coding
       | assistants make it easy to translate thought to code. So much
       | boilerplate can be given to the assistant to write out while you
       | focus on system design, architecture, etc, and then just guide
       | the AI system to generate the code for you.
        
       | wakefulsales wrote:
       | this is just stupid, anyone who's used ai to code knows this is
       | wrong empirically
        
         | recursive wrote:
         | I've used it and haven't had much success.
        
       | dukeofdoom wrote:
       | It's more like an assistant that can help you write a class to do
       | something. You could write on your own but feeling lazy.
       | Sometimes it's good, other times it's idioticly bad. Need to keep
       | it in check and keep telling it what it needs to do because it
       | has a tendency to dig holes it can't get out of. Breaking things
       | up into Smaller classes helps to a degree.
        
       | incoming1211 wrote:
       | I'm sorry to say, but the author of this post doesn't appear to
       | have much, if any experience with AI and sounds like he's just
       | trying to justify not using it and pretend hes better without it.
        
         | cedws wrote:
         | It's okay to be a sceptic, I am too, but the logic and
         | reasoning in the post is just really flimsy and makes our
         | debate look weak.
        
           | permo-w wrote:
           | seriously. if you want to say that AI will likely reduce
           | wages and supply for certain more boilerplate jobs; or that
           | they are comparatively much worse for the environment than
           | normal coding; or that they are not particularly good once
           | you get into something quite esoteric or complex; or that
           | they've led certain companies to think that developing AGI is
           | a good idea; or that they're mostly centralised into the
           | hands of a few unpleasant actors; then any of those
           | criticisms, and certainly others, are valid to me, but to say
           | that they're not actually useful or provide little value?
           | it's just nonsense or ragebait
        
       | tensor wrote:
       | "Spellcheck provides little value because an authors job is to
       | write." - rolls eyes
        
       | kace91 wrote:
       | These articles keep popping up, analyzing an hypothetical usage
       | of AI (and guessing it won't be useful) as if it wasn't something
       | already being used in practice. It's kinda weird to me.
       | 
       | "It won't deal with abstractions" -> try asking cursor for
       | potential refactors or patterns that could be useful for a given
       | text.
       | 
       | "It doesn't understand things beyond the code" -> try giving them
       | an abstract jira ticket or asking what it things about certain
       | naming, with enough context
       | 
       | "Reading code and understanding whether it's wrong will take more
       | time than writing it yourself" -> ask any engineer that saves
       | time with everything from test scaffolding to run-and-forget
       | scripts.
       | 
       | It's as if I wrote an article today arguing that exercise won't
       | make you able to lift more weight - every gymgoer would raise an
       | eyebrow, and it's hard to imagine even the non-gymgoers would be
       | sheltered enough to buy the argument either.
        
         | tyleo wrote:
         | Agreed. It isn't like crypto where the proponents proclaimed
         | some use case that would prove value always on the verge of
         | arriving. AI is useful right now. People are using these tools
         | now and enjoying them.
        
           | jdiff wrote:
           | I'm not sure that's a convincing argument given that crypto
           | heads haven't just been enthusiastically chatting about the
           | possibilities in the abstract. They do an awful lot of that,
           | see Web3, but they _have_ been using crypto.
        
           | awesome_dude wrote:
           | I don't (use AI tools), I've tried them and found that they
           | got in the way, made things more confusing, and did not get
           | me to a point where the thing I was trying to create was
           | working (let alone working well/safe to send to prod)
           | 
           | I am /hoping/ that AI will improve, to the point that I can
           | use it like Google or Wikipedia (that is, have some trust in
           | what's being produced)
           | 
           | I don't actually know anyone using AI right now. I know one
           | person on Bluesky has found it helpful for prototyping things
           | (and I'm kind of jealous of him because he's found how to get
           | AI to "work" for him).
           | 
           | Oh, I've also seen people pasting AI results into serious
           | discussions to try and prove the experts wrong, but only to
           | discover that the AI has produced flawed responses.
        
             | tptacek wrote:
             | _I don 't actually know anyone using AI right now._
             | 
             | I believe you, but this to me is a wild claim.
        
               | awesome_dude wrote:
               | Ha! I think the same way when I see people saying that AI
               | is in widespread use - I believe that it's possible, but
               | it feels like an outlandish claim
        
               | LanceJones wrote:
               | I'd say 500M WAUs on chatGPT alone qualifies as
               | widespread use.
        
               | awesome_dude wrote:
               | Ok, how much of that is developers using it to help them
               | code?
        
             | plsbenice34 wrote:
             | Essentially the same for me, I had one incident where
             | someone was arguing in favor of it and then immediately
             | embarrassed themselves badly because they were misled by a
             | chatgpt error. I have the feeling that this hype will
             | collapse as this happens more and people see how bad the
             | consequences are when there are errors
        
           | plsbenice34 wrote:
           | Even in 2012 bitcoin could very concretely be used to order
           | drugs. Many people have used it to transact and preserve
           | value in hostile economic environments. Etc etc. Ridiculous
           | comment.
           | 
           | Personally i have still yet to find LLMs useful at all with
           | programming.
        
         | crispinb wrote:
         | It's the barstool economist argument style, on long-expired
         | loan from medieval theology. Responding to clear empirical
         | evidence that X occurs: "X can't happen because [insert
         | 'rational' theory recapitulation]"
        
         | Kapura wrote:
         | weird metaphor, because a gym goer practices what they are
         | doing by putting in the reps in order to increase personal
         | capacity. it's more like you're laughing at people at the gym,
         | saying "don't you know we have forklifts already lifting much
         | more?"
        
           | asadotzler wrote:
           | "If you want to be good at lifting, just buy an exoskeleton
           | like me and all my bros have. Never mind that your muscles
           | will atrophy and you'll often get somersaulted down a flight
           | of stairs while the exoskeleton makers all keep trying, and
           | failing, to contain the exoskeleton propensity for tossing
           | people down flights of stairs."
        
           | cgriswald wrote:
           | I see it as almost the opposite. It's like the pulley has
           | been invented but some people refuse to acknowledge its
           | usefulness and make claims that you're weaker if you use it.
           | But you can grow quite strong working a pulley all day.
        
           | kace91 wrote:
           | That's a completely different argument, however, and a good
           | one to have.
           | 
           | I can buy "if you use the forklift you'll eventually lose the
           | ability to lift weight by yourself", but the author is going
           | for "the forklift is actually not able to lift anything"
           | which can trivially be proven wrong.
        
         | jstummbillig wrote:
         | Well said. It's not that there would not be much to seriously
         | think about and discuss - so much is changing, so quickly - but
         | the stuff that a lot of these articles focus is a strange
         | exercise in denial.
        
         | amelius wrote:
         | If AI gives a bad experience 20% of the time, and if there are
         | 10M programmers using it, then about 3000 of them will have a
         | bad experience 5 times in a row. You can't really blame them
         | for giving up and writing about it.
        
         | charlie-83 wrote:
         | Out if interest, what kind of codebases are you able to get AI
         | to do these things on. Everytime I have tried it with even
         | simpler things than these it has failed spectacularly. Every
         | example I see of people doing this kind of thing seems to be on
         | some kind if web development so I have a hypothesis that AI
         | might currently be much worse for the kinds of codebases I work
         | on.
        
           | idontwantthis wrote:
           | That's my experience too. It also fails terribly with
           | ElasticSearch probably because the documentation doesn't have
           | a lot of examples. ChatGPT, copilot and claude were all
           | useless for that and gave completely plausible nonsense. I've
           | used it with most success for writing unit tests and
           | definitely shell scripts.
        
           | kace91 wrote:
           | I currently work for a finance-related scaleup. So backend
           | systems, with significant challenges related to domain
           | complexity and scalability, but nothing super low level
           | either.
           | 
           | It does take a bit to understand how to prompt in a way that
           | the results are useful, can you share what you tried so far?
        
             | charlie-83 wrote:
             | I have tried on a lot of different projects.
             | 
             | I have a codebase in Zig and it doesn't understand Zig at
             | all.
             | 
             | I have another which is embedded C using zephyr RTOS. It
             | doesn't understand zephyr at all and even if it could, it
             | can't read the documentation for the different sensors nor
             | can it plug in cables.
             | 
             | I have a tui project in rust using ratatui. The core of the
             | project is dealing with binary files and the time it takes
             | to explain to it how specific bits of data are organised in
             | the file and then check it got everything perfectly correct
             | (it never has) is more than the time to just write the
             | code. I expect I could have more success on the actual TUI
             | side of things but haven't tried too much since I am trying
             | to learn rust with this project.
             | 
             | I just started an android app with flutter/dart. I get the
             | feeling it will work well for this but I am yet to verify
             | since I need to learn enough flutter to be able to judge it
             | 
             | My dayjob is a big C++ codebase making a GUI app with Qt.
             | The core of it is all dealing with USB devices and
             | Bluetooth protocols which it doesn't understand at all. We
             | also have lots of very complicated C++ data structures, I
             | had hoped that the AI would be able to at least explain
             | them to me but it just makes stuff up everytime. This also
             | means that getting it to edit any part of the codebase
             | touching this sort if thing doesn't work. It just rips up
             | any thread safety or allocates memory incorrectly etc. It
             | also doesn't understand the compiler errors at all, I had a
             | circular dependency and tried to get it to solve it but I
             | had to give so many clues I basically told it what the
             | problem was.
             | 
             | I really expected it to work very well for the Qt interface
             | since building UI is what everyone seems to be doing with
             | it. But the amount of hand holding it requires is insane.
             | Each prompt feels like a monkey's paw. In every experiment
             | I've done it would have been faster to just write it
             | myself. I need to try getting it to write an entirely new
             | pice of UI from scratch since I've only been editing
             | existing UI so far.
             | 
             | Some of this is clearly a skill issue since I do feel
             | myself getting better at prompting it and getting better
             | results. However, I really do get the feeling that it
             | either doesn't work or doesn't work as well on my code
             | bases as other ones.
        
           | doug_durham wrote:
           | I work in Python, Swift, and Objective-C. AI tools work great
           | in all of these environment. It's not just limited to web
           | development.
        
             | charlie-83 wrote:
             | I suppose saying that I've only seen it in web development
             | is a bit of an exaggeration. It would be more accurate to
             | say that I haven't seen any examples of people using AI on
             | a codebase that looks like on of the ones I work on.
             | Clearly I am biased just lump all the types of coding I'm
             | not interested in into "web development"
        
         | thenaturalist wrote:
         | While I tend to agree with your premise that the linked article
         | seems to be reasoning to the extreme off the basis of a very
         | small code snippet, I think the core critique the author wants
         | to make stands:
         | 
         | AI agents alone, unbounded, currently cannot provide huge
         | value.
         | 
         | > try asking cursor for potential refactors or patterns that
         | could be useful for a given text.
         | 
         | You, the developer, will be selecting this text.
         | 
         | > try giving them an abstract jira ticket or asking what it
         | things about certain naming, with enough context
         | 
         | You still selected a JIRA ticket and provided context.
         | 
         | > ask any engineer that saves time with everything from test
         | scaffolding to run-and-forget scripts.
         | 
         | Yes that is true, but again, what you are providing as a
         | counterfactual are very bounded, aka easy contexts.
         | 
         | In any case, the industry (both the LLM providers as well as
         | tooling builders and devs) is clearly going into the direction
         | of constantly etching out small imoprovements by refining which
         | context is deemed relevant for a given problem and most
         | efficient ways to feed it to LLMs.
         | 
         | And let's not kid ourselves, Microsoft, OpenAI, hell Anthropic
         | all have 2027-2029 plans where these things will be
         | significantly more powerful.
        
           | tptacek wrote:
           | Why does it matter that you're doing the thinking? Isn't that
           | good news? What we're not doing any more is any the rote
           | recitation that takes up most of the day when building stuff.
        
           | tomnipotent wrote:
           | I think maybe you have unrealistic expectations.
           | 
           | Yesterday I needed to import a 1GB CSV into ClickHouse. I
           | copied the first 500 lines into Claude and asked it for a
           | CREATE TABLE and CLI to import the file. Previous day I was
           | running into a bug with some throw-away code so I pasted the
           | error and code into Claude and it found the non-obvious
           | mistake instantly. Week prior it saved me hours converting
           | some early prototype code from React to Vue.
           | 
           | I do this probably half a dozen times a day, maybe more if
           | I'm working on something unfamiliar. It saves at a minimum an
           | hour a day by pointing me in the right direction - an answer
           | I would have reached myself, but slower.
           | 
           | Over a month, a quarter, a year... this adds up. I don't need
           | "big wins" from my LLM to feel happy and productive with the
           | many little wins it's giving me today. And this is the worst
           | it's ever going to be.
        
           | viraptor wrote:
           | In lots of jobs, the person doing work is not the one
           | selecting text or the JIRA ticket. There's lots of "this is
           | what you're working on next" coding positions that are fully
           | managed.
           | 
           | But even if we ignored those, this feels like goalpost
           | moving. They're not selecting the text - ok, ask LLM what
           | needs refactoring and why. They're not selecting the JIRA
           | ticket with context? Ok, provide MCP to JIRA, git and comms
           | and ask it to select a ticket, then iterate on context until
           | it's solvable. Going with "but someone else does the step
           | above" applies to almost everyone's job as well.
        
           | danielschreber wrote:
           | >etching out
           | 
           | Could you explain what you mean by etching out small
           | improvements? I've never seen the phrase "etching out"
           | before.
        
         | verelo wrote:
         | It's all good to me - let these folks stay in the simple times
         | while you and i arbitrage our efforts against theirs? I agree,
         | there's massive value in using these tools and it's hilarious
         | to me when others don't see it. My reaction isn't going to be
         | convince them they're wrong, it's just to find ways to use it
         | to get ahead while leaving them behind.
        
         | Glyptodon wrote:
         | I don't know. Cursor is decent at refactoring. ("Look at x and
         | ____ so that it ____." With some level of elaboration, where
         | the change is code or code organization centric.)
         | 
         | And it's okay at basic generation - "write a map or hash table
         | wrapper where the input is a TZDB zone and the output is
         | ______" will create something reasonable and get some of the
         | TZDB zones wrong.
         | 
         | But it hasn't been that great for me at really extensive
         | conceptual coding so far. Though maybe I'm bad at prompting.
         | 
         | Might be there's something I'm missing w/ my prompts.
        
         | skydhash wrote:
         | > _"It won't deal with abstractions" - > try asking cursor for
         | potential refactors or patterns that could be useful for a
         | given text._
         | 
         | That is not what abstraction is about. Abstraction is having a
         | simpler model to reason about, not simply code rearranging.
         | 
         | > _"It doesn't understand things beyond the code" - > try
         | giving them an abstract jira ticket or asking what it things
         | about certain naming, with enough context_
         | 
         | Again, that is still pretty much coding. What matters is the
         | overall design (or at least the current module).
         | 
         | > _"Reading code and understanding whether it's wrong will take
         | more time than writing it yourself" - > ask any engineer that
         | saves time with everything from test scaffolding to run-and-
         | forget scripts._
         | 
         | Imagine having a script and not checking the man pages for
         | expected behavior. I hope the backup games are strong.
        
         | tptacek wrote:
         | There really is a category of these posts that are coming from
         | some alternate dimension (or maybe we're in the alternate
         | dimension and they're in the real one?) where this isn't one of
         | the most important things ever to happen to software
         | development. I'm a person who didn't even use autocomplete (I
         | use LSPs almost entirely for cross-referencing --- oh wait
         | that's another thing I'm apparently never going to need to do
         | again because of LLMs), a sincere tooling skeptic. I do not
         | understand how people expect to write convincingly that tools
         | that reliably turn slapdash prose into median-grade idiomatic
         | working code "provide little value".
        
           | quesera wrote:
           | > _tools that reliably turn slapdash prose into median-grade
           | idiomatic working code_
           | 
           | This may be the crux of it.
           | 
           | Turning slapdash prose into median-grade code is not a
           | problem I can imagine trying to solve.
           | 
           | I think I'm better at describing code _in code_ than I am in
           | prose.
           | 
           | And when I ask for some algorithmic "save me a web search"
           | help, e.g. "In Ruby using no external gems, implement the
           | Chudnovsky algorithm to calculate the first N digits of Pi",
           | the results I get are absurd, despite explicit assurances
           | that the code is tested (often it won't even parse, and yes I
           | know there's no Ruby interpreter inside, but why lie?), and
           | simpering gratitude when I repeatedly point out obvious
           | lexical problems like assigning constants in a loop.
           | 
           | I Want to Believe. And I certainly don't want to be "that
           | guy", but my honest assessment of LLMs for coding so far is
           | that they are a frustrating Junior, who maybe I should help
           | out because mentoring might be part of my job, but from whom
           | I should not expect any near-term technical contribution.
        
             | tptacek wrote:
             | It is most of the problem of delivering professional
             | software.
        
         | agentultra wrote:
         | I don't think the argument from such a simple example does much
         | for the authors point.
         | 
         | The bigger risk is skill atrophy.
         | 
         | Proponents say, it doesn't matter. We shouldn't have to care
         | about memory allocation or dependencies. The AI system will
         | eventually have all of the information it needs. We just have
         | to tell it what we want.
         | 
         | However, knowing what you want requires knowledge about the
         | subject. If you're not a security engineer you might not know
         | what funny machines are. If someone finds an exploit using them
         | you'll have no idea what to ask for.
         | 
         | AI may be useful for some but at the end of the day, knowledge
         | is useful.
        
       | dymk wrote:
       | And yet I keep meeting programmers who say AI coding assistants
       | are saving them tons of time or helping them work through
       | problems they otherwise wouldn't have been able to tackle. I
       | count myself among that group at this point. Maybe that means I'm
       | just not a very good programmer if I need the assistance, but I'd
       | like to think my work speaks for itself at this point.
       | 
       | Some things where I've found AI coding assistants to be fantastic
       | time savers:                 - Searching a codebase with natural
       | language       - Quickly groking the purpose of a function or
       | file or module       - Rubber duck debugging some particularly
       | tricky code       - Coming up with tests exercising functionality
       | I hadn't yet considered       - Getting up to speed with popular
       | libraries and APIs
        
       | WhitneyLand wrote:
       | If it's of such little value, does he really want to compete
       | against developers trying to do the same thing he is but that
       | have the benefit of it?
        
       | minimaxir wrote:
       | > But AI doesn't think -- it predicts patterns in language.
       | 
       | Boilerplate code _is_ a pattern, and code is a language. That 's
       | part of why AI-generated code is especially effective for simple
       | tasks.
       | 
       | It's when you get into more complicated apps that the pros/cons
       | of AI coding start to be more apparent.
        
         | permo-w wrote:
         | not even necessarily complicated, but also obscure
        
       | gersh wrote:
       | It seems like the traditional way to develop good judgement is by
       | getting experience with hands-on coding. If that is all
       | automated, how will people get the experience to have good
       | judgement? Will fewer people get the experiences necessary to
       | have good judgement?
        
         | nico wrote:
         | Compilers, for the most part, made it unnecessary for
         | programmers to check the assembly code. There are still
         | compiler programmers that do need to deal with that, but most
         | programmers get to benefit from just trusting that the
         | compilers, and by extension the compiler programmers, are doing
         | a good job
         | 
         | We are in a transition period now. But eventually, most
         | programmers will probably just get to trust the AIs and the
         | code they generate, maybe do some debugging here and there at
         | the most. Essentially AIs are becoming the English -> Code
         | compilers
        
           | asadotzler wrote:
           | In my experience, compilers are far more predictable and
           | consistent than LLMs, making them suitable for their purpose
           | in important ways that LLMs are not.
        
           | permo-w wrote:
           | I honestly think people are so massively panicking over
           | nothing with AI. even wrt graphic design, which I think
           | people are most worried about, the main, central skill of a
           | graphic designer is not the actual graft of sitting down and
           | drawing the design, it's having the taste and skill and
           | knowledge to make design choices that are worthwhile and
           | useful and aesthetically pleasing. I can fart around all day
           | on Stable Diffusion or telling an LLM to design a website,
           | but I don't know shit about UI/UX design or colour theory or
           | simply what appeals to people visually, and I doubt an AI can
           | teach me it to any real degree.
           | 
           | yes there are now likely going to be less billable hours and
           | perhaps less joy in the work, but at the same time I suspect
           | that managers who decide they can forgo graphic designers and
           | just get programmers to do it without someone trained AI are
           | going to lose a competitive advantage
        
       | Falimonda wrote:
       | I fear this will not age well.
       | 
       | Which models have you tried to date? Can you come up with a top 3
       | ranking among popular models based on your definition of value?
       | 
       | What can be said about the ability of an LLM to translate your
       | thinking represented in natural language to working code at rates
       | exceeding 5-10x your typing speed?
       | 
       | Mark my words: Every single business that has a need for SWEs
       | will obligate their SWEs to use AI coding assistants by the end
       | of 2026, if not by the end of 2025. It will not be optional like
       | it is today. Now is the time you should be exploring which models
       | are better at "thinking" than others, and discerning which
       | thinking you should be doing vs. which thinking you can leave up
       | to ever-advancing LLMs.
        
         | jdiff wrote:
         | I've had to yank tokens out of the mouths of too many thinking
         | models stuck in loops of (internally, within their own chain of
         | thought) rephrasing the same broken function over and over
         | again, realizing each time that it doesn't meet constraints,
         | and trying the same thing again. Meanwhile, I was sat staring
         | at an opaque spinner wondering if it would have been easier to
         | just write it myself. This was with Gemini 2.5 Pro for
         | reference.
         | 
         | Drop me a message on New Year's Day 2027. I'm betting I'll
         | still be using them optionally.
        
           | Falimonda wrote:
           | I've experienced gemini get stuck as you describe a handful
           | of times. With that said, my predication is made on the
           | observation that these tools are already force multipliers,
           | and they're only getting better each passing quarter.
           | 
           | You'll of course be free to use them optionally in your free
           | time and on personal projects. It won't be the case at your
           | place of employment.
           | 
           | I will mark my calendar!
        
         | marcusb wrote:
         | This reminds me of the story a few days ago about "what is your
         | best prompt to stump LLMs", and many of the second level
         | replies were links to current chat transcripts where the LLM
         | handled the prompt without issue.
         | 
         | I think there are a couple of problems at play: 1) people who
         | don't want the tools to have value, for various reasons, and
         | have therefore decided the tools don't have value; 2) people
         | who tried the tools six months or a year ago and had a bad
         | experience and gave up; and 3) people who haven't figured out
         | how to make good use of the tools to improve their productivity
         | (this one seems to be heavily impacted by various grifters who
         | overstate what the coding assistants can do, and people
         | underestimating the effort they have to put in to get good at
         | getting good output from the models.)
        
       | tomschwiha wrote:
       | One point AI helps me with is to keep going.
       | 
       | Does it do things wrong (compared to what I have in my mind?). Of
       | course. But it helps to have code quicker on screen. Editing /
       | rolling back feels faster than typing everything myself.
        
       | rcarmo wrote:
       | 4 lines of JS. A screenful of "reasoning". Not much I can agree
       | with.
       | 
       | Meanwhile I just asked Gemini in VS Code Agent Mode to build an
       | HTTP-like router using a trie and then refactor it as a Python
       | decorator, and other than a somewhat dumb corner case it failed
       | at, it generated a pretty useful piece of code that saved me a
       | couple of hours (I had actually done this before a few years ago,
       | so I knew exactly what I wanted).
       | 
       | Replace programmers? No. Well, except front-end (that kind of
       | code is just too formulaic, transactional and often boring to
       | do), and my experiments with React and Vue were pretty much "just
       | add CSS".
       | 
       | Add value? Heck yes - although I am still very wary of letting
       | LLM-written code into production without a thorough review.
        
         | jdiff wrote:
         | Not even front end, unless it literally is a dumb thin wrapper
         | around a back end. If you are processing anything on that front
         | end, AI is likely to fall flat as quickly as it would on the
         | backend.
        
           | permo-w wrote:
           | based on what?
        
             | jdiff wrote:
             | My own experience writing a web-based, SVG-based 3D
             | modeler. No traditional back end, but when working on the
             | underlying 3D engine it shits the bed from all the broken
             | assumptions and uncommon conventions used there. And in the
             | UI, the case I have in mind involved pointer capture and
             | event handling, it chases down phantoms declaring it's
             | working around behavior that isn't in the spec. I bring it
             | the spec, I bring it minimal examples producing the desired
             | behavior, and it still can't produce working code. It still
             | tries to critique existing details that aren't part of the
             | problem, as evidenced by the fact it took me 5 minutes to
             | debug and fix myself when I got tired of pruning context.
             | At one point it highlighted a line of code and suggested
             | the problem could be a particular function getting called
             | after that line. That function was called 10 lines above
             | the highlighted line, in a section it re-output in a quote
             | block.
             | 
             | So yes, it's bad for front end work too if your front end
             | isn't just shoveling data into your back end.
             | 
             | AI's fine for well-trodden roads. It's awful if you're
             | beating your own path, and especially bad at treading a new
             | path just alongside a superhighway in the training data.
        
               | permo-w wrote:
               | it built the meat of the code, you spent 5 minutes fixing
               | the more complex and esoteric issues. is this not the
               | desired situation? you saved time, but your skillset
               | remained viable
               | 
               | > AI's fine for well-trodden roads. It's awful if you're
               | beating your own path, and especially bad at treading a
               | new path just alongside a superhighway in the training
               | data.
               | 
               | I very much agree with this, although I think that it can
               | be ameliorated significantly with clever prompting
        
         | jolt42 wrote:
         | > that kind of code is just too formulaic, transactional and
         | often boring to do
         | 
         | No offense, but that sounds like every programmer that hasn't
         | done front-end development to me. Maybe for some class of
         | front-ends (the same stuff that Ruby on Rails could generate),
         | but past that things tend to get not boring real fast.
        
         | nottorp wrote:
         | > I had actually done this before a few years ago, so I knew
         | exactly what I wanted
         | 
         | Oh :) LLMs do work sometimes when you already know what you
         | want them to write.
        
       | greatpostman wrote:
       | Honestly, o3 has completely blown my mind in terms of ability to
       | come up with useful abstractions beyond what I would normally
       | build. Most people claiming LLMs are limited just arent using the
       | tools enough, and cant see the trajectory of increasing ability
        
         | quesera wrote:
         | > _Most people claiming LLMs are limited just rent using the
         | tools enough_
         | 
         | The old quote might apply:
         | 
         | ~"XML is like violence. If it's not working for you, you need
         | to use more of it".
         | 
         | (I think this is from Tim Bray -- it was certainly in his
         | .signature for a while -- but oddly a quick web search doesn't
         | give me anything authoritative. I asked Gemma3, which suggests
         | Drew Conroy instead)
        
       | meander_water wrote:
       | A programmers job is to provide value to the business. Thinking
       | is certainly a part of the process, but not the job in itself.
       | 
       | I agree with the initial point he's making here - that code takes
       | time to parse mentally, but that does not naturally lead to the
       | conclusion that this _is_ the job.
        
       | kristopolous wrote:
       | It's the "Day-50" problem.
       | 
       | On Day-0, AI is great but by Day-50 there's preferences and
       | nuance that isn't captured through textual evidence. The
       | productivity gains mostly vanish.
       | 
       | Ultimately AI coding efficacy is an HCI relationship and you need
       | different relationships (workflows) at different points in time.
       | 
       | That's why, currently, as time progresses you use AI less and
       | less on any feature and fall back to human. Your workflow isn't
       | flexible enough.
       | 
       | You don't need to tell me you do this, everyone does.
       | 
       | So the real problem isn't the Day-0 solution, it's solving the
       | HCI workflow problem to get productivity gains at Day-50.
       | 
       | Smarter AI isn't going to solve this. Large enough code becomes
       | internally contradictory, documentation becomes dated, tickets
       | become invalid, design docs are based on older conceptions.
       | Devin, plandex, aider, goose, claude desktop, openai codex, these
       | are all Day-0 relationships. The best might be a Day-10 solution,
       | but none are Day-50.
       | 
       | The future world of GPT-5 and Sonnet-4 still won't read your
       | thoughts.
       | 
       | Day-50 productivity is ultimately a user-interface problem - a
       | relationship negotiation and a fundamentally dynamic
       | relationship.
       | 
       | I talked about what I'm doing to empower new workflows over here:
       | https://news.ycombinator.com/item?id=43814203
        
         | Bengalilol wrote:
         | You pinpoint a truly important thing, even though I cannot put
         | words onto it, I think that getting lost with AI coding
         | assistants is far worse than getting lost as a programmer. It
         | is like doing vanilla code or trying to make a framework suit
         | your needs.
         | 
         | AI coding assistants provide 90% of the time more value than
         | the good old google search. Nothing more, nothing less. But I
         | don't use AI to code for me, I just use it to optimize very
         | small fractions (ie: methods/functions at most).
         | 
         | > The future world of GPT-5 and Sonnet-4 still won't read your
         | thoughts. Chills ahead. For sure, it will happen some day. And
         | there won't be any reason to not embrace it (although I am, for
         | now, absolutely reluctant to such idea).
        
       | ChrisMarshallNY wrote:
       | I haven't been using AI for coding assistance. I use it like
       | someone I can spin around in my chair, and ask for any ideas.
       | 
       | Like some knucklehead sitting behind me, sometimes, it has given
       | me good ideas. Other times ... _not so much_.
       | 
       | I have to carefully consider the advice and code that I get.
       | Sometimes, it works, but it does not work _well_. I don 't think
       | that I've ever used suggested code verbatim. I _always_ need to
       | modify it; sometimes, heavily.
       | 
       | So I still have to think.
        
       | calf wrote:
       | Do non-AI coding assistants provide value?
        
       | moshegramovsky wrote:
       | It doesn't seem like the author has ever used AI to write code.
       | You definitely can ask it to refactor. Both ChatGPT and Gemini
       | have done excellent work for me on refactors, and they have also
       | made mistakes. It seems like they are both quite good at making
       | lengthy, high-quality suggestions about how to refactor code.
       | 
       | His argument about debugging is absolutely asinine. I use both
       | GDB and Visual Studio at work. I hate Visual Studio except for
       | the debugger. GDB is definitely better than nothing, but only
       | just. I am way, way, way more productive debugging in Visual
       | Studio.
       | 
       | Using a good debugger can absolutely help you understand the code
       | better and faster. Sorry but that's true whether the author likes
       | it or not.
        
       | robertclaus wrote:
       | In the past I've worked at startups that hired way too many
       | bright junior developers and at companies that insisted on only
       | hiring senior developers. The arguments for/against AI coding
       | assistants feel very reminiscent of the arguments that occur
       | around what seniority balance we want on an engineering team. In
       | my experience it's a matter of balancing between doing complex
       | work yourself and handing off simple work.
        
       | bastawhiz wrote:
       | I have not had the same experience as the author. The code I have
       | my tools write is not long. I write a little bit at a time, and I
       | know what I expect it to generate before it generates it. If what
       | it generates isn't what I expect, that's a good hint to me that I
       | haven't been descriptive enough with my comments or naming or
       | method signatures.
       | 
       | I use Cursor not because I want it to think for me, but because I
       | can only type so fast. I get out of it exactly the amount of
       | value that I expect to get out of it. I can tell it to go through
       | a file and perform a purely mechanical reformatting (like
       | converting camel case to snake case) and it's faster to review
       | the results than it is for me to try some clever regexp and screw
       | it up five or six times.
       | 
       | And quite honestly, for me that's the dream. Reducing the
       | friction of human-machine interaction is _exactly the goal_ of
       | designing good tools. If there was no meaningful value to be had
       | from being able to get my ideas into the machine faster, nobody
       | would buy fancy keyboards or (non-accessibility) dictation
       | software.
        
       | mrtksn wrote:
       | Software ate the world, it's time for AI to eat the software :)
       | 
       | Anything methodical is exactly what the current gen AI can do.
       | Its phenomenal in translations, be it human language to human
       | language or an algorithm description into computer language.
       | 
       | People like to make fun with the "vibe coding" but that's
       | actually a purification process where humans are getting rid of
       | the toolset that we used to master to be able to make the
       | computer do what we tell it to do.
       | 
       | Most of todays AI developer tools are misguided because they are
       | trying to orchestrate tools that were created to help people
       | write and manage software.
       | 
       | IMHO the next-gen tools will write code that is not intended for
       | human consumption. All the frameworks, version management, coding
       | paradigms etc will be relics of the past. Curiosities for people
       | who are fascinated for that kind of things, not production
       | material.
        
       | beernet wrote:
       | Call it AI, ML, Data Mining, it does not matter. Truth is these
       | tools have been disrupting the SWE market and will continue to do
       | so. People working with it will simply be more effective. Until
       | even them are obsolete. Don't hate the player, hate the game.
        
       | androng wrote:
       | If AI coding assistants provide little value then why is Cursor
       | IDE a 300m company and why does this study say it makes people
       | more 37% more productive?
       | 
       | https://exec.mit.edu/s/blog-post/the-productivity-effects-of...
        
         | hooloovoo_zoo wrote:
         | That study shows nothing of the sort. It essentially showed
         | ChatGPT is better at pumping out boilerplate than humans. Here
         | are the tasks:
         | https://www.science.org/action/downloadSupplement?doi=10.112...
        
       | einpoklum wrote:
       | Reading just the title:
       | 
       | It is _because_ a programmer's job is to think that AI Coding
       | assistants may provide value. They would (and perhaps already do)
       | complete the boiler plate, and perhaps help you access
       | information faster. They also have detriments, may atrophy some
       | of your capabilities, may tempt you to go down more simplistic
       | paths etc., but still.
       | 
       | Reading the post as well: It didn't change my mind. As for what
       | it actually says, my reaction is a shrug, "whatever".
        
       | tangotaylor wrote:
       | I think there's some truth here in that AI can be used as a band-
       | aid to sweep issues of bad abstractions or terse syntax under the
       | rug.
       | 
       | For example, I often find myself reaching for Cursor/ChatGPT to
       | help me with simple things in bash scripts (like argument
       | parsing, looping through arrays, associative maps, handling
       | spaces in inputs) because the syntax just isn't intuitive to me.
       | But I can easily do these things in Python without asking an AI.
       | 
       | I'm not a web developer but I imagine issues of boilerplate or
       | awkward syntax could be solved with more "thinking" instead of
       | using the AI as a better abstraction to the bad abstractions in
       | your codebase.
        
       | WillPostForFood wrote:
       | _engineering workflows should be more about thinking and
       | discussing than writing code_
       | 
       | This is also the best case for using AI. You think, you discuss,
       | then instruct the AI to write, then you review.
        
       | Velorivox wrote:
       | Title is a bit provocative and begs the question (is thinking the
       | part being replaced?), but the bigger issue is what "little"
       | means here. Little in absolute terms? I think that's harsh.
       | Little in relation to how it's touted? That's a rational
       | conclusion, I think.
       | 
       | You need three things to use LLM based tools effectively: 1) an
       | understanding of what the tool is good at and what it isn't good
       | at; 2) enough context and experience to input a well formulated
       | query; and 3) the ability to carefully verify the output and
       | discard it if necessary.
       | 
       | This is the same skillset we've been using with search engines
       | for years, and we know that not everyone has the same degree of
       | Google-fu. There's a lot of subjectivity to the "value".
        
       | rashidae wrote:
       | I believe we need to take a more participatory approach to
       | intelligence orchestration.
       | 
       | It's not humans vs machines.
        
       | henning wrote:
       | I am the first to criticize LLMs and dumb AI hype. there is no
       | nothing wrong with using an LSP, and a coding assistant is just
       | an enhanced LSP if that is all you want it to be. my job is to
       | solve problems, and AI can slightly speed that up.
        
       | rybosworld wrote:
       | This is a tired viewpoint.
       | 
       | There's a percentage of developers, who due to fear/ego/whatever,
       | are refusing to understand how to use AI tooling. I used to
       | debate but I've started to realize that these arguments are
       | mostly not coming from a rational place.
        
       | SkyPuncher wrote:
       | I get massive value out of Agentic coding.
       | 
       | I no longer need to worry about a massive amount of annoying, but
       | largely meaningless implementation details. I don't need to pick
       | a random variable/method/class name out of thin air. I don't need
       | to plan ahead on how to DRY up a method. I don't need to consider
       | every single edge case up front.
       | 
       | Sure, I still need to tweak and correct things but we're talking
       | about paint by number instead of starting with a blank canvas.
       | It's such a massive reduction in mental load.
       | 
       | I also find it reductionist to say LLM don't think because
       | they're simply predicting patterns. Predicting patterns is
       | thinking. With the right context, there is little difference
       | between complex pattern matching and actual thinking. Heck, a
       | massive amount of my actual, professional software development
       | work is figuring out how to pattern matching my idea into an
       | existing code base. There's a LOT of value in consistency.
        
       | merizian wrote:
       | I prefer a more nuanced take. If I can't reliably delegate away a
       | task, then it's usually not worth delegating. The time to review
       | the code needs to be less than the time it takes to write it
       | myself. This is true for people and AI.
       | 
       | And there are now many tasks which I can confidently delegate
       | away to AI, and that set of tasks is growing.
        
       | gamescr wrote:
       | Some problems require using a different kind of modeling other
       | than language:
       | 
       | https://medium.com/@lively_burlywood_cheetah_472/ai-cant-sol...
        
       ___________________________________________________________________
       (page generated 2025-04-27 23:00 UTC)