[HN Gopher] Ask HN: AI productivity gains - do you fire devs or ...
___________________________________________________________________
Ask HN: AI productivity gains - do you fire devs or build better
products?
i was rolling my eyes at the hype, but _reading_ about this is
totally different from _experiencing_ it. if you have any old repos
out there - try it, you might actually be amazed. i'm not sure i
buy the long-term "*90% productivity*" claims for complex, legacy
enterprise systems, but for the boilerplate, libraries, build-
tools, and refactoring? the gain is gigantic. all the time-
consuming, nerve-wrecking stuff is mostly taken care of. you start
off checking every diff like a hawk, expecting it to break things,
but honestly, soon you see it's not necessary most of the time. you
just keep your IDE open and feed the "analyze code" output back
into it. in java, telling it to " _add checkstyle, run mvn verify
and repair_ " works well enough that you can actually go grab a
coffee instead of fighting linter warnings. the theory is that
what remains is just the _logic_ and _ideas_. we 'll see how that
holds up when the architecture gets genuinely tangled. but for now,
letting it branch off, create boilerplate, and write a simple test
while you just iterate on the spec works shockingly well. you only
write source code when it's too annoying to write down the spec in
plain english. it raises the real question: if your competitor Y
just fired 90% of their developers to save a buck, would you
blindly follow suit? or would you keep your team, use this massive
leverage, and just *dwarf* Y with a vastly better product?
Author : Bleiglanz
Score : 78 points
Date : 2026-03-22 09:37 UTC (13 hours ago)
| aurareturn wrote:
| In certain industries, increasing productivity by 90% does not
| mean 90% increase in profit. This is because growth depends on
| market TAM and growth rate.
|
| Another way of increasing profit is to simply reduce your
| headcount by 90% while keeping the same profit.*
|
| Hence, I think some companies will keep downsizing. Some
| companies will hire. It depends a lot.
|
| *Assuming 90% productivity increase.
| muzani wrote:
| In companies like the oil industry, doubling productivity would
| mean reducing the expected life span. Costs tend to catch up
| with profits, especially due to taxes. Layoffs happen
| inevitably.
|
| Is it the same with tech? Facebook has 3 billion monthly active
| users. No amount of tech will bring that up to 6 billion. If
| you were to double the amount of time someone spends on
| Facebook, or double the ads they see or double the click
| through rate, what does that really mean?
| aurareturn wrote:
| Yeah, even if Meta engineers gain 90% increase in
| productivity, I doubt Meta can increase revenue by 90% more
| than previous environment. There's just a cap to how much
| time people want to spend on social media.
|
| I think most companies are making the right call by
| downsizing instead of staying same size. Let people go to
| where there is more potential for growth.
| hirako2000 wrote:
| That's assuming a company is constrained, to not expand its
| portfolio.
|
| Taking the example of Facebook. They are in social media,
| messaging, AI, VR/AR hardware and software, a few other
| things, meta universe whatever that was, now left with the
| name. Facebook isn't delivering or successful on all its
| ventures, it knows that, it keeps investing in other
| segments.
|
| More productivity would mean at least diversifying, they have
| some of the best engineers, it would make no sense to not
| simply attempt to hit the jackpot by playing more machines.
|
| What fewer people talks about is that the entire tech
| industry is tertiary services. Ads, entertainment,
| communication, etc. If/when hard industries take a hit,
| tertiary takes a hit. If it isn't clear to you that the
| overall economy has already started to take some irreversible
| dents, and that those will accelerate, know that the capital
| is well aware.
|
| Or we can continue wishful thinking and seek comfort that
| monetary tightening is just temporary, investments will flow
| more into tangent ventures and growth is around the corner,
| the U.S still is and will remain the world's strongest
| economy.
| _wire_ wrote:
| "I just got my third coffee and I'm feeling really good about the
| quality of this code. I don't even bother to look at it. Keeps my
| tests simple to not test at all. You know, 'in theory'. Of course
| when the architecture gets genuinely tangled... Just keep your
| IDE open so the code knows where to go. Whoa, too much caffeine,
| super sleepy..."
|
| Terafab is suddenly making so much sense!
| Throaway1975123 wrote:
| "ugh, what a hard day at work, I had to prompt the LLM for 8
| hours!!"
| lordkrandel wrote:
| Why do people keep ralking about AI as it actually worked? I
| still don't see ANY proof that it doesn't generate a total
| unmaintainable unsecure mess, that since you didn't develop, you
| don't know how to fix. Like running a F1 Ferrari on a countryside
| road: useless and dangerous
| the_real_cher wrote:
| Yeah its great but as the OP said you have to watch every P.R.
| like a hawk
| FromTheFirstIn wrote:
| OP said you stop doing that at some point
| tyleo wrote:
| Because it's working for a lot of people. There are people
| getting value from these products right now. I'm getting value
| myself and I know several other folks at work who are getting
| value.
|
| I'm not sure what your circumstances are but even if it's not
| true for you, it's true for many other people.
| pydry wrote:
| It's interesting that the people IRL I encounter who "get the
| most value" tend to be the devs who couldnt distinguish well
| written code from slop in the first place.
|
| People online with identical views to them all assure me that
| theyre all _highly_ skilled though.
|
| Meanwhile I've been experimenting using AI for shopping and
| all of them so far are horrendous. Cant handle basic queries
| without tripping over themselves.
| tyleo wrote:
| > I've been experimenting using AI for shopping
|
| This is an interesting choice for a first experiment. I
| wouldn't personally base AI's utility for all other things
| on its utility for shopping.
| pydry wrote:
| It's not a first experiment it's experiment 50 or 60 and,
| a reaction to AI gaslighting.
|
| Most people dont really understand coding but shopping is
| a _far_ simpler task and so it 's easier to see how and
| where it fails (i.e. with even mildly complex
| instructions).
| tyleo wrote:
| Do you mind sharing examples of the prompts you are
| using?
| AStrangeMorrow wrote:
| Idk basically everyone is my org has seen some good value
| out of it. We have people complaining about limitations,
| but would still rather have that tooling than not.
|
| For me the main difference is now some people can explain
| what their code does. While some other only what it wants
| to achieve
| hermannj314 wrote:
| If you are a 2600 chess player, a bot that plays 1800 chess
| is a horrendous chess player.
|
| But you can understand why all the 1700 and below chess
| players say it is good and it is making them better using
| it for eval?
|
| Don't worry, AI will replace you one day, you are just
| smarter than most of us so you don't see it yet.
| roncesvalles wrote:
| The analogy of thinking of coding AI like it's chess AI
| is terrible. If chess AI was at the level of coding AI,
| it wouldn't win a single game.
|
| This kind of thinking is actually a big reason why execs
| are being misinformed into overestimating LLM abilities.
|
| LLM coding agents alone are not good enough to replace
| any single developer. They only make _a_ developer x%
| faster. _That dev_ who is now x% faster may then allow
| you to lay off another dev. That is a subtle yet critical
| difference.
| lugu wrote:
| I like the chess analogy as it answer the question: why
| can't i see those gain?
|
| To adress your point, let's try another one analogy.
| Imagine secreterial assistants, discussing their risk of
| been replaced by computers in the 80s. They would think:
| someone still need to type those letters, sit next to
| that phone and make those appointments, I am safe.
| Computers won't replace me.
|
| It is not that AI will do all of your tasks and replace
| you. It is that your role as a specialist in software
| development won't be necessary most of the time (someone
| will do that, and that person won't call themselves a
| programmer).
| roncesvalles wrote:
| Secretarial assistant as a profession is still very
| alive, and the title has been inflated to stratospheric
| heights (and compensation): "Chief of Staff"
| Kim_Bruning wrote:
| Consider it this way as a reasoning step: We've invented a
| cross compiler that can handle the natural languages too.
| That's definitely useful; but it's still GIGO so you still need
| your brain.
| thefounder wrote:
| You can launch a new product in one month instead of 12 months.
| I think this works best for startups where the risk tolerance
| is high but works less than ideal for companies such Amazon
| where system failure has high costs
| dominotw wrote:
| so where are these one man products lauched in a month?
|
| not talking about toys or vibecoded crap no one uses.
| fragmede wrote:
| Aside from the things people have launched that don't count
| because I'm right, where are the things that have been
| launched?
| dominotw wrote:
| apps with actual users is too high of a bar now?
| Throaway1975123 wrote:
| probs look in the game space to see a bunch of muggles
| making money off of "vibe coded" software
| deaux wrote:
| They're here, I made one. Not a toy or vibecoded crap,
| people got immediate value. Not planning to doxx myself by
| linking it. This was more than a year ago when models
| weren't even as good yet. A year later it has thousands of
| consistent monthly users, and it only keeps growing. It's
| nothing compared to VC startups but for a solo dev, made in
| a month? Again, it's not a toy, it offers new functionality
| that simply didn't exist yet and it improves people's
| lives. The reality is that there's no chance I would've
| done it without LLMs.
| UqWBcuFx6NV4r wrote:
| This is delusional. Are you someone that tends to have your
| finger on the pulse of every piece of software ever
| released, as it's being released, with knowledge about how
| it's built? You're not.
|
| Nobody is.
|
| Perhaps nobody cares to "convince you" and "win you over",
| because...why? Why do we all have to spoon feed this one to
| you while you kick and scream every step of the way?
|
| If you don't believe it, so be it.
| gamblor956 wrote:
| Real ones don't exist. Conveniently, nobody that has
| claimed to have created a functional AI product is willing
| to "doxx themselves" by linking to their app.
|
| Weirdly, people who have actually created functional one-
| man products don't seem to have the same problem, as they
| welcome the business.
| giantg2 wrote:
| I see more value on the business side than the tech side. Ask
| the AI to transcribe images, write an email, parse some excel
| data, create a prototype, etc. Some of which you might have
| hired a tech resource to write a script for.
|
| On the tech side I see it saving some time with stuff like mock
| data creation, writing boiler plate, etc. You still have to
| review it like it's a junior. You still have to think about the
| requirements and design to provide a detailed understanding to
| them (AI or junior).
|
| I don't think either of these will provide 90% productivity
| gains. Maybe 25-50% depending on the job.
| lukev wrote:
| I agree, but absence of evidence is not evidence of absence,
| and we currently have a lot of developers who _feel_ very
| productive right now.
|
| We are very much in need of an actual way to measure real
| economic impact of AI-assisted coding, over both shorter and
| longer time horizons.
|
| There's been an absolute rash of vibecoded startups. Are we
| seeing better success rates or sales across the industry?
| ThrowawayR2 wrote:
| > " _absence of evidence is not evidence of absence_ "
|
| That's the same false argument that the religious have
| offered for their beliefs and was debunked by Bertrand
| Russell's teapot argument:
| https://en.wikipedia.org/wiki/Russell%27s_teapot
| fbrncci wrote:
| It works. You're just not doing it right if it doesn't work for
| you. It's hard to convince me otherwise at this point.
| UqWBcuFx6NV4r wrote:
| Person that can't use a hammer "hasn't seen any proof" that
| hammers work.
| alexjplant wrote:
| > Why do people keep ralking about AI as it actually worked?
|
| Because it does.
|
| > I still don't see ANY proof that it doesn't generate a total
| unmaintainable unsecure mess, that since you didn't develop,
| you don't know how to fix.
|
| I wouldn't know since it's been years since I've tried but I'd
| imagine that Claude Code would indeed generate a half-baked
| Next.js monstrosity if one-shot and left to its own devices.
| Being the learned software engineer I am, however, I provide it
| plenty of context about architecture and conventions in a
| bootstrapped codebase and it (mostly) obeys them. It still
| makes mistakes frequently but it's not an exaggeration to say
| that I can give it a list of fields with validation rules and
| query patterns and it'll build me CRUD pages in a fraction of
| the time it'd take me to do so.
|
| I can also give it a list of sundry small improvements to make
| and it'll do the same, e.g. I can iterate on domain stuff while
| it fixes a bunch of tiny UX bugs. It's great.
| K0balt wrote:
| I've been using it to develop firmware in c++. Typically around
| 10-20 KLOC. Current projects use Sensors, wire protocols, RF
| systems , swarm networks, that kind of stuff integrated into
| the firmware.
|
| If you use it correctly, you can get better quality, more
| maintainable code than 75% of devs will turn in on a PR. The
| "one weird trick" seems to be to specify, specify, specify.
| First you use the LLM to help you write a spec (document, if
| it's pre existing). Make sure the spec is correct and matches
| the user story and edge cases. The LLM is good at helping here
| too. Then break down separations of concerns, APIs, and
| interfaces. Have it build a dependency graph. After each step,
| have it reevaluate the entire stack to make sure it is clear,
| clean, and self consistent.
|
| Every step of this is basically the AI doing the whole thing,
| just with guidance and feedback.
|
| Once you've got the documentation needed to build an actual
| plan for implementation, have it do that. Each step, you go
| back as far as relevant to reevaluate. Compare the spec to the
| implementation plan, close the circle. Then have it write the
| bones, all the files and interfaces, without actual
| implementations. Then have it reevaluate the dependency graph
| and the plan and the file structure together. Then start
| implementing the plan, building testing jigs along the way.
|
| You just build software the way you used to, but you use the
| LLM to do most of the work along the way. Every so often,
| you'll run into something that doesn't pass the smell test and
| you'll give it a nudge in the right direction.
|
| Think of it as a junior dev that graduated top of every class
| ever, and types 1000wpm.
|
| Even after all of that, I'm turning out better code, better
| documentation, and better products, and doing what used to take
| 2 devs a month, in 3 or 4 days on my own.
|
| On the app development side of our business, the productivity
| gain also strong. I can't really speak to code quality there,
| but I can say we get updates in hours instead of days, and
| there are less bugs in the implementations. They say the code
| is better documented and easier to follow , because they're not
| under pressure to ship hacky prototype code as if it were
| production.
|
| On the current project, our team size is 1/2 the size it would
| have been last year, and we are moving about 4x as fast. What
| doesn't seem to scale for us is size. If we doubled our team
| size I think the gains would be very small compared to the
| costs. Velocity seems to be throttled more by external factors.
|
| I really don't understand where people are coming from saying
| it doesn't work. I'm not sure if it's because they haven't
| tried a real workflow, or maybe tried it at all, or they are
| definitely "holding it wrong." It works. But you still need
| seasoned engineers to manage it and catch the occasional bad
| judgment or deviation from the intention.
|
| If you just let it, it will definitely go off the rails and
| you'll end up with a twisted mess that no one can debug. But
| use a system of writing the code incrementally through a
| specification - evaluation loop as you descend the abstraction
| from idea to implementation you'll end up winning.
|
| As a side note, and this is a little strange and I might be
| wrong because it's hard to quantify and all vibes, but:
|
| I have the AI keep a journal about its observations and general
| impressions, sort of the "meta" without the technical details.
| I frame this to it as a continuation of "awareness " for new
| sessions.
|
| I have a short set of "onboarding" documents that describe the
| vision, ethos, and goals of the project. I have it read the
| journal and the onboarding docs at the beginning of each
| session.
|
| I frame my work with the AI as working with it as a
| "collaborator" rather than a tool. At the end of the day, I
| remind it to update its journal of reflections about the days
| work. It's total anthropomorphism, obviously, but it seems to
| inspire "trust" in the relationship, and it really seems to up-
| level the effort that the AI puts in. It kinda makes sense,
| LLMs being modelled on human activity.
|
| FWIW, I'm not asserting anything here about the nature of
| machine intelligence, I'm targeting what seems to create the
| best result. Eventually we will have to grapple with this I
| imagine, but that's not today.
|
| When I have forgotten to warm-start the session, I find that I
| am rejecting much more of the work. I think this would be worth
| someone doing an actual study to see if it is real or some kind
| of irresistible cognitive bias.
|
| I find that the work produced is much less prone to going off
| the rails or taking shortcuts when I have this in the context,
| and by reading the journal I get ideas on where and how to do a
| better job of steering and nudging to get better results. It's
| like a review system for my prompting. The onboarding docs seem
| to help keep the model working towards the big picture? Idk.
|
| This "system" with the journal and onboarding only seems to
| work with some models. GPT5 for example doesn't seem to benefit
| from the journal and sometimes gets into a very creepy vibe. I
| think it might be optimized for creating some kind of
| "relationship" with the user.
| systemsweird wrote:
| This is one of the best descriptions of using AI effectively
| I've read. It becomes clear that using AI effectively is
| about planning, architecture, and directing another
| intelligent agent. It's essential to get things right at each
| high level step before drilling in deeper as you clearly
| outlined.
|
| I suspect you either already were or would've been great at
| leading real human developers not just AI agents. Directing
| an AI towards good results is shockingly similar to directing
| people. I think that's a big thing separating those getting
| great results with AI from those claiming it simply does not
| work. Not everyone is good at doing high level panning,
| architecture, and directing others. But those that already
| had those skills basically just hit the ground running with
| AI.
|
| There are many people working as software engineers who are
| just really great at writing code, but may be lacking in the
| other skills needed to effectively use AI. They're the angry
| ones lamenting the loss of craft, and rightfully so, but
| their experience with AI doesn't change the shift that's
| happening.
| AStrangeMorrow wrote:
| For me, the main thing is to never have it write anything based
| on the goal (what the end result should look like and how it
| should behave). And only on the implementation details (and
| coding practices that I like).
|
| Sure it is not as fast to understand as code I wrote. But at
| least I mostly need to confirm it followed how it implemented
| what I asked. Not figuring out WHAT it even decided to
| implement in the first place.
|
| And in my org, people move around projects quite a bit. Hasn't
| been uncommon for me to jump in projects with 50k+ lines of
| code a few times a year to help implement a tricky feature, or
| help optimize things when it runs too slow. Lots of code to
| understand then. Depending on who wrote it, sometimes it is
| simple: one or two files to understand, clean code. Sometimes
| it is an interconnected mess and imho often way less organized
| that Ai generated code.
|
| And same thing for the review process, lots of having to
| understand new code. At least with AI you are fed the changes a
| a slower pace.
| MrScruff wrote:
| I see a lot of people talk about 'insecure code' and while I
| don't doubt that's true, there's a lot of software development
| where security isn't actually a concern because there's no need
| for the software to be 'secure'. Maintainability is important
| I'll grant you.
| iExploder wrote:
| yes you fire if you are a burned out company that only needs to
| maintain its product and slowly die...
|
| you hire more if you are growth and have new ideas just never had
| the chance to implement them as they were not practical of
| feasible at that level of tech (non-assisted humans clicking code
| and taking sick leaves)
| conartist6 wrote:
| Gotta fire everyone, or else "too many cooks" will mean that even
| those temporary productivity gains go up in smoke.
|
| Remember sometimes the most productive thing to have is not money
| or people but time with your ideas.
| conartist6 wrote:
| What's so sad to see is people excited about making something
| selling away the time they would have with their ideas. They're
| paying money to not use their brain to contemplate the thing
| they should be the foremost expert in the world on, and they're
| _excited_ to be paying more and more for each modicum of
| ignorance and mediocrity dispensed.
| giantg2 wrote:
| I feel like the ideas have always been the tough part. Finding
| novel ideas with a good return is extremely tough.
| jaen wrote:
| That's assuming every developer can get the same AI efficiency
| boost and contribute meaningfully to _any_ feature, which is
| unfortunately not really the case.
|
| Seniors can adjust, but eg. junior frontend-only devs might be
| doomed in both situations, as they might not be able to
| contribute _enough_ to business-critical features to justify
| their costs and most frontend-related tasks will be taken over by
| the "10x" seniors.
| matt_s wrote:
| Developers are going to be more productive, just not how you
| think. If history is going to rhyme, then the software industry
| will enter into a self-serving productivity craze building all
| sorts of software tooling, frameworks, ralph wiggum loop
| variants, MCPs, etc. much like the surge in JS frameworks and
| variants in the past. Most of those things will not have any
| business value. Software devs, myself included, love to do things
| "because I can" and not necessarily because they should.
|
| Smart organizations will not just deliver better products but
| likely start products that they were hesitant to start before
| because the cost of starting is a lot closer to zero. Smart
| engineering leadership will encourage developers into delivering
| value and not self-serving, endless iterations of tooling
| enhancements, etc.
|
| If I was a CTO and my competitor Y fired 90% of their devs, I'd
| try to secure funding to hire their top talent and retain them.
| The vitriol alone could fuel some interesting creations and when
| competitor Y realizes things later, their top talent will have
| moved on.
| MichaelRo wrote:
| >> then the software industry will enter into a self-serving
| productivity craze building all sorts of software tooling,
| frameworks
|
| >> Smart organizations will not just deliver better products
| but likely start products [...]
|
| This is not the 90s anymore when low hanging fruit was
| everywhere ready to be picked. We have everything under the sun
| now and more.
|
| The problem with bullshit apps is not that it took you 5 months
| to build. What you build now in 5 minutes it's still bullshit.
| Most of the remaining work is bullshit jobs. Spinning useless
| "features" and frameworks that nobody needs and shove them down
| the throat of customers that never asked for them. Now it's
| possible to dig holes and fill them back (do pointless work) at
| much improved pace thanks to AI.
| marcyb5st wrote:
| If I were to run the company potentially mostly focus on better
| products with the exception of firing those that don't adopt the
| technology.
|
| If it is a big company the answer is and will always be: whatever
| makes the stock price rise the most.
| elvis10ten wrote:
| > with the exception of firing those that don't adopt the
| technology.
|
| This is a crazy take. Even if said people are matching or
| exceeding the outcome of those using the technology?
|
| I'm not in this group. But the closest analog to what you are
| saying is firing people for not using a specific IDE.
| NotGMan wrote:
| Why not both?
| rsynnott wrote:
| > boilerplate
|
| Ruby on Rails and its imitators blew away tons of boilerplate.
| Despite some hype at the time about a productivity revolution, it
| didn't _really_ change that much.
|
| > , libraries, build-tools,
|
| Ensure what you mean by this; what bearing do our friends the
| magic robots have on these?
|
| > and refactoring
|
| Again, IntelliJ did not really cause a productivity revolution by
| making refactoring trivial about 20 years ago. Also, refactoring
| is kind of a solved problem, due to IntelliJ et al; what's an LLM
| getting you there that decent deterministic tooling doesn't?
| rileymichael wrote:
| couldn't have said it better. all of the people clamoring on
| about eliminating the boilerplate they've been writing +
| enabling refactoring have had their heads in the sand for the
| past two decades. so yeah, i'm sure it does seem revolutionary
| to them!
| maccard wrote:
| There have been a handful of leaps - copilot was able to look
| at open files and stub out a new service in my custom
| framework, including adding tests. It's not a multiplier but
| it certainly helps
| rileymichael wrote:
| most frameworks have CLIs / IDE plugins that do the same
| (plus models, database integration, etc.)
| deterministically. i've built many in house versions for
| internal frameworks over the years. if you were writing a
| ton of boilerplate prior to LLMs, that was on you
| maccard wrote:
| Habe they? I've used tools that mostly do it, but they
| require manually writing templates for the frameworks. In
| internal apps my experience has been these get left
| behind as the service implementations change, and it ends
| up with "copy your favourite service that you know
| works".
| rileymichael wrote:
| > they require manually writing templates for the
| frameworks
|
| the ones i've used come with defaults that you can then
| customize. here are some of the better ones:
|
| - https://guides.rubyonrails.org/command_line.html#genera
| ting-...
|
| - https://hexdocs.pm/phoenix/Mix.Tasks.Phx.Gen.html
|
| - https://laravel.com/docs/13.x/artisan#stub-
| customization
|
| - https://learn.microsoft.com/en-
| us/aspnet/core/fundamentals/t...
|
| > my experience has been these get left behind as the
| service implementations change
|
| yeah i've definitely seen this, ultimately it comes down
| to your culture / ensuring time is invested in devex. an
| approach that helps avoid drift is generating directly
| from an _actual_ project instead of using something like
| yeoman, but that's quite involved
| maccard wrote:
| Sorry - I'm aware that rails/dotnet have these built into
| visual studio and co, but my point was about our custom
| internal things that are definitely not IDE integrated.
|
| > it comes down to ensuring time is invested in devex
|
| That's actually my point - the orgs haven't invested in
| devex buyt that didn't matter because copilot could
| figure out what to do!
| epicureanideal wrote:
| And for a lot of AI transformation tasks, for a long time I've
| been using even clever regex search/replace, and with a few
| minutes of small adjustment afterward I have a 100%
| deterministic (or 95% deterministic and 5% manually human
| reviewed and edited) process for transforming code. Although of
| course I haven't tried that cross-language, etc.
|
| And of course, we didn't see a massive layoff after the
| introduction of say, StackOverflow, or DreamWeaver, or jQuery
| vs raw JS, Twitter Bootstrap, etc.
| elvis10ten wrote:
| I just had a relevant experience. I asked Claude to add
| "trace('$FunctionName') {}" to all Composable functions in my
| app. Claude spent some time doing something. In between, I
| was like shoot, I could just do a deterministic regex match
| and replace.
| rileymichael wrote:
| structural search and replace in intellij is a superpower
| (within a single repo). for polyrepo setups, openrewrite is
| great. add in an orchestrator (simple enough to build one
| like sourcegraph's batch changes) and you can manage hundreds
| of repositories in a deterministic, testable way.
| j45 wrote:
| You have your devs be engineering managers over the tools.
| dare944 wrote:
| False dichotomy. If your company is at the point of firing lots
| of people "to save a buck" its way past the point of caring about
| delivering a better product.
| GenerWork wrote:
| >do you fire devs or build better products?
|
| I think that it's more along the lines of "do you fire people"
| instead of just "do you fire devs". Fewer devs means less of a
| need for PMs, so they can be let go as well, and maybe with the
| rise of AI assisted design tools, you don't need as many UX
| people, so you let some of them go as well.
|
| As for building better products, I feel like that's a completely
| different topic than using AI for productivity gains, but only
| because at the end of the day you need buy in from upper
| management in order to build the features/redo existing
| features/both that will make the product better. I should also
| mention I'm viewing this from the position of someone who works
| at an established company and not a startup, so it may differ.
| gedy wrote:
| Productivity really means nothing across companies and the
| software industry. So we code faster, but honestly problem I see
| is companies ask us to code stupid or worthless things in many
| cases.
|
| CTO is rewriting company platform (by himself with AI) and is
| convinced it's 100x productivity. But when you step back and look
| at the broader picture, he's rewriting what something like Rails,
| .NET, or Spring gave us 15-20 years ago? It's just in languages
| and code styles he is (only) familiar with. That's not 100x for
| the business, sorry...
| animal531 wrote:
| I use it near daily and there is definitely a positive there, BUT
| its nothing like what the OP statement would make it up to be.
|
| If it is writing both the code and the tests then you're going to
| find that its tests are remarkable, they just work. At least
| until you deploy to a live state and start testing for yourself,
| then you'll notice that its mostly only testing the exact code
| that it wrote, its not confrontational or trying to find errors
| and it already assumes that its going to work. It won't ever come
| up with the majority of breaking cases that a developer will by
| itself, you will need to guide it. Also while fixing those the
| odds of introducing other breaking changes are decent, and after
| enough prompts you are going to lose coherency no matter what you
| do.
|
| It definitely makes a lot of boilerplate code easier, but what
| you don't notice is that its just moving the difficult to find
| problems into hidden new areas. That fancy code that it wrote
| maybe doesn't take any building blocks, lower levels such as
| database optimization etc. into account. Even for a simple
| application a half-decent developer can create something that
| will run quite a bit faster. If you start bringing these problems
| to it then it might be able to optimize them, but the amount of
| time that's going to take is non-negligible.
|
| It takes developers time to sit on code, learn it along with the
| problem space and how to tie them together effectively. If you
| take that away there is no learning, you're just the monkey copy-
| pasting the produced output from the black box and hoping that
| you get a result that works. Even worse is that every step you
| take doesn't bring you any closer to the solution, its pretty
| much random.
|
| So what is it good for? It can both read, "understand",
| translate, write and explain things to a sufficient degree much
| faster than us humans. But if you are (at the moment) trusting it
| at anything past the method level for code then you're just
| shooting yourself in the foot, you're just not feeling the pain
| until later. In a day you can have it generate for example a
| whole website, backend, db etc. for your new business idea but
| that's not a "product", it might as well be a promotional video
| that you throw away once you've used it to impress the investors.
| For now that might still work, but people are already catching on
| and beginning to wise up.
| anon7725 wrote:
| This is the most insightful comment in the thread.
| kakacik wrote:
| Don't break the gravy train! These discussions here are
| beautiful echo chambers.
|
| I feel like most folks commenting uncritically here about
| second coming of Jesus must work in some code sweatshops,
| churning eshops or whatever is in vogue today quickly and
| moving on, never looking back, never maintaining and working on
| their codebases for decade+. Where I existed my whole career,
| speed of delivery was never the primary concern, quality of
| delivery (which everybody unanimously complaints one way or
| another with llms) was much more critical and thats where the
| money went. Maybe I just picked up right businesses, but then
| again I worked for energy company, insurance, telco,
| government, army, municipality, 2 banks and so on across 3
| European states. Also, full working code delivery to production
| is a rather small part of any serious project, even 5x speed
| increase would move the needle just a tiny bit overall.
|
| If I would be more junior, I would feel massive FOMO from
| reading all this (since I use it so far just as a quicker
| google/stackoverflow and some simpler refactoring, but oh boy
| is is sometimes hilariously and dangerously wrong). I am not,
| thus I couldn't care less. Node.js craze, 10x stronger, not
| seeing forest for the trees.
| intoXbox wrote:
| The pain already starts when a new feature needs to be
| introduced, your colleague is assigned to the task and the
| architecture is completely unfit for modular development.
|
| Any sensible experienced programmer will take into account
| possible future features spoken about around the office, when
| deciding how implement a feature. To me that's the key reason I
| can't delegate AI complex features that will grow. The same
| reason I inspect and clean the toilet when I'm done - out of
| respect to my colleagues
| capitalsigma wrote:
| This is more or less my belief too. But I think there are
| probably domains/companies where the "promo video" is actually
| good enough to ship (or at least, where that's the quality that
| devs were shipping before)
| gamblor956 wrote:
| AI tooling does not provide productivity gains unless you
| consider it productive to skip the boilerplate portion of
| software development, which you can already do by using a
| framework, or you never plan to get past the MVP stage of a
| product, as refactoring the AI spaghetti would take several
| magnitudes more work than doing it with humans from the
| beginning.
|
| Amazon has demonstrated that it takes just as longer, or longer,
| to have senior devs review LLM output than it would to just have
| the senior devs do the programming in the first place. But now
| your senior devs are wasted on reviewing instead of developing or
| engineering. Amazon, Microsoft, Google, Salesforce, and Palantir
| have all suffered _multiple_ losses in the tens of millions (or
| more) due to AI output issues. Now that Microsoft has finally
| realized how bad LLMs really are at generating useful output,
| they 've begun _removing_ AI functionality from Windows.
|
| Product quality matters more than time to market. Especially in
| tech, the first-to-market is almost never the company that
| dominates, so it's truly bizarre that VCs are always so focused
| on their investments trying to be first to market instead of best
| to market.
|
| If Competitor Y just fired 90% of their developers, I would have
| a toast with my entire _human_ team. And a few months later, we
| 'd own the market with our superior product.
| bendmorris wrote:
| It's disappointing that this is clearly being downvoted due to
| disagreement - it's a valid perspective. We have very little
| evidence of the overall impact of aggressively generating code
| "in the wild" and plenty of bad examples. No one knows what
| this ends up looking like as it continues to meet reality but
| plenty are taking a large productivity improvement as a given.
| hirako2000 wrote:
| Assuming you are primarily selling software.
|
| Situation a/ llm increase developer's productivity: you hire more
| developers as you cash profit. If you don't your competitor will.
|
| b/ llm doesn't increase productivity, you keep cruising. You
| rejoice seeing some competitors lay off.
|
| Reality shows dissonance with these only possible scenarios.
| Absurd decision making, a mistake? No mistake. Many tech
| companies are facing difficulties, they need to lose weight to
| remain profitable, and appease the shareholders demand for bigger
| margins.
|
| How to do this without a backlash? Ai is replacing developers,
| Anthropic's CEO said engineers don't write code anymore, role
| obsolete in 6 months. It naturally makes sense we have to let
| some of them go. If the prophecy doesn't turn true, nobody ever
| get fired for buying IBM.
| lateforwork wrote:
| You still need humans to manage the whole lifecycle, including
| monitoring the live site, being on-call, handling incidents,
| triaging bugs, deploying fixes, supporting users and so on.
|
| For greenfield development you don't need as many software
| engineers. Some developers (the top 10%) are still needed to
| guide AI and make architectural decisions, but the remaining 90%
| will work on the lifecycle management task mentioned above.
|
| The productivity gains can be used to produce more software, and
| if you are able to sell the software you produce should result in
| a revenue boost. But if you produce more than you can sell then
| some people will be laid off.
| ashwinnair99 wrote:
| The companies quietly doing the firing will say they're doing the
| building. The answer you get depends entirely on who you ask and
| what they're trying to justify.
| HoyaSaxa wrote:
| I think most public companies will take the short term profits
| and startups will be given a huge opportunity to take market
| share as a result.
|
| At my company, we are maintaining our hiring plan (I'm the
| decision maker). We have never been more excited at our
| permission to win against the incumbents in our market. At the
| same time, I've never been more concerned about other startups
| giving us a real run. I think we will see a bit of an arms race
| for the best talent as a result.
|
| Productivity without clear vision, strategy and user feedback
| loops is meaningless. But those startups that are able to harness
| the productivity gains to deliver more complete and polished
| solutions that solve real problems for their users will be
| unstoppable.
|
| We've always seen big gains by taking a team of say 8 and
| splitting it into 2 teams of 4. I think the major difference is
| that now we will probably split teams of 4 into 2 teams of 2 with
| clearer remits. I don't want them to necessarily delivery more
| features. But I do want them to deliver features with far fewer
| caveats at a higher quality and then iterate more on those.
|
| Humans that consume the software will become the bottlenecks of
| change!
| maccard wrote:
| > try it, you might actually be amazed.
|
| I keep being told this and the tools keep falling at the first
| hurdle. This morning I asked Claude to use a library to load a
| toml file in .net and print a value. It immediately explained how
| it was an easy file format to parse and didn't need a library. I
| undid, went back to plan mode and it picked a library, added it
| and claimed it was done. Except the code didn't compile.
|
| Three iterations later of trying to get Claude to make it compile
| (it changed random lines around the clear problematic line) I
| fixed it by following the example in the readme, and told Claude.
|
| I then asked Claude to parse the rest of the toml file, whereby
| it blew away the compile fix I had made..
|
| This isn't an isolated experience - I hit these fundamental
| blocking issues with pretty much every attempt to use these tools
| that isn't "implement a web page", and even when it does that
| it's not long before it gets tangled up in something or other...
| krastanov wrote:
| This is fascinating to me. I completely believe you and I will
| not bother you with all the common "but did you try to tell it
| this or that" responses, but this is such a different
| experience from mine. I did the exact same task with claude in
| the Julia language last week, and everything worked perfectly.
| I am now in the habit of adding "keep it simple, use only
| public interfaces, do not use internals, be elegant and
| extremely minimal in your changes" to all my requests or
| SKILL.md or AGENTS.md files (because of the occasional failure
| like the one you described). But generally speaking, such
| complete failures have been so very rare for me, that it is
| amazing to see that others have had such a completely different
| experience.
| shafyy wrote:
| It's almost like.... LLMs are non-deterministic and
| hallucinating... Oh wait?!
| krastanov wrote:
| non-deterministic does not mean it is not biased towards a
| particular type of results (helpful results)
| jayd16 wrote:
| You say it doesn't fail but you also mention all these work
| around you know and try...sounds like it fails a lot but your
| tolerance is different.
| zorak8me wrote:
| Providing instruction and context doesn't seem like a
| "workaround".
| plagiarist wrote:
| IME it does fail pretty hard at first. One has to build up
| a little library of markdown and internal library of prompt
| techniques. Then it starts working okay. I agree there is a
| hurdle still, trying it on one task doesn't really get one
| over the hurdle.
| jmalicki wrote:
| Most people I've seen complain say things like "I asked it
| for code and it didn't compile."
|
| The real magic of LLMs comes when they iterate until
| completion until the code compiles and the test passes, and
| you don't even bother looking at it until then.
|
| Each step is pretty stupid, but the ability to very quickly
| doggedly keep at it until success quite often produces
| great work.
|
| If you don't have linters that are checking for valid
| syntax and approved coding style, if you don't have tests
| to ensure the LLM doesn't screw up the code, you don't have
| good CI, you're going to have a bad time.
|
| LLMs are just like extremely bright but sloppy junior devs
| - if you think about putting the same guardrails in place
| for your project you would for that case, things tend to
| work very well - you're giving the LLM a chance to check
| its work and self correct.
|
| It's the agentic loop that makes it work, not the single-
| shot output of an LLM.
| alecbz wrote:
| Stuff like this works for things that can be verified
| programmatically (though I find LLMs still do
| occasionally ignore instructions like this), but ensuring
| correct functionality and sensible code organization are
| bigger challenges.
|
| There are techniques that can help deal with this but
| none of them work perfectly, and most of the time some
| direct oversight from me is required. And this really
| clips the potential productivity gains, because in order
| to effectively provide oversight you need to page in all
| the context of what's going on and how it ought to work,
| which is most of what the LLMs are in-theory helping you
| with.
|
| LLMs are still very useful for certain tasks
| (bootstrapping in new unfamiliar domains, tedious
| plumbing or test fixture code), but the massive
| productivity gains people are claiming or alluding to
| still feel out of reach.
| jmalicki wrote:
| It depends - there are some very very difficult things
| that can still be easily verifiable!
|
| For instance, if you are working on a compiler and have a
| huge test database of code to compile that all has tests
| itself, "all sample code must compile and pass tests,
| ensuring your new optimizer code gets adequate branch
| coverage in the process" - the underlying task can be
| very difficult, but you have large amounts of test
| coverage that have a very good chance at catching errors
| there.
|
| At the very least "LLM code compiles, and is formatted
| and documented according to lint rules" is pretty basic.
| If people are saying LLM code doesn't compile, then yes,
| you are using it very incorrectly, as you're not even
| beginning to engage the agentic loop _at all_ , as
| compiling is the simplest step.
|
| Sure, a lot of more complex cases require oversight or
| don't work.
|
| But "the code didn't compile" is definitely in "you're
| holding it wrong" territority, and it's not even subtle.
| alecbz wrote:
| Yeah performance optimization is potentially another good
| area for LLMs to shine, _if_ you already have a
| sufficiently comprehensive test suite, because no
| functionality is changing. But if functionality is
| changing, you need to be in the loop to, at the very
| least, review the tests that the LLM outputs. Sometimes
| that 's easier than reviewing the code itself, but other
| times I think it requires similar levels of context.
|
| But honestly I think sane code organization is the bigger
| hurdle, which is a lot harder to get right without manual
| oversight. Which of course leads to the temptation to
| give up on reviewing the code and just trusting whatever
| the LLM outputs. But I'm skeptical this is a viable
| approach. LLMs, like human devs, seem to need reasonably
| well-organized code to be able to work in a codebase, but
| I think the code they output often falls short of this
| standard.
|
| (But yes agree that getting the LLM to iterate until CI
| passes is table-stakes.)
| jmalicki wrote:
| Strongly agreed!
|
| I think getting good code organization out of an LLM is
| one of the subtler things - I've learned quite a bit
| about what sort of things need to be specified, realizing
| that the LLM isn't actively learning my preferences
| particularly well, so there are some things about code
| organization I just have to be explicit about.
|
| Which is more work, but less work than just writing the
| code myself to begin with.
| aqua_coder wrote:
| My experience with working with AI agents is that they can be
| verbose and do things that are too over complicated by
| default. Unless directed explicitly. Which may be the reason
| for this discrepancy.
| wrs wrote:
| I'm honestly baffled by this. I don't want to tell you "you're
| holding it wrong" but if this is your normal experience there's
| something weird happening.
|
| Friday afternoon I made a new directory and told Claude Code I
| wanted to make a Go proxy so I could have a request/callback
| HTTP API for a 3rd party service whose official API is only
| persistent websocket connections. I had it read the service's
| API docs, engage in some back and forth to establish the
| architecture and library choices, and save out a phased
| implementation plan in plan mode. It implemented it in four
| phases with passing tests for each, then did live tests against
| the service in which it debugged its protocol mistakes using
| curl. Finally I had it do two rounds of code review with fresh
| context, and it fixed a race condition and made a few things
| cleaner. Total time, two hours.
|
| I have noticed some people I work with have more trouble, and
| my vague intuition is it happens when they give Claude too much
| autonomy. It works better when you tell it what to do, rather
| than letting it decide. That can be at a pretty high level,
| though. Basically reduce the problem to a set of well-
| established subproblems that it's familiar with. Same as you'd
| do with a junior developer, really.
| shireboy wrote:
| Similar. I regularly use Github copilot (with claude models
| sometimes) and it works amazingly. But I see some who
| struggle with them. I have sort of learned to talk to it,
| understand what it is generating, and routinely use to
| generate fixes, whole features, etc. much much faster than I
| could before.
| thwarted wrote:
| > _it happens when they give Claude too much autonomy. It
| works better when you tell it what to do, rather than letting
| it decide. That can be at a pretty high level, though.
| Basically reduce the problem to a set of well-established
| subproblems that it's familiar with. Same as you'd do with a
| junior developer, really._
|
| Equating "junior developers" and "coding LLMs" is pretty
| lame. You handhold a junior developers so, eventually, you
| don't have to handhold anymore. The junior developer is
| expected to learn enough, and be trusted enough, to operate
| more autonomously. "Junior developers" don't exist solely to
| do your bidding. It may be valuable to recognize similarities
| between a first junior developer interaction and a first LLM
| interaction, but when _every_ LLM interaction requires it to
| be handheld, the value of the iterative nature of having a
| junior developer work _along side you_ is not at all
| equivalent.
| wrs wrote:
| I didn't say they are equivalent, nor do I in any way
| consider them equivalent. One is a tool, the other is a
| person.
|
| I simply said the description of the problem should be
| broken down similar to the way you'd do it for a junior
| developer. As opposed to the way you'd express the problem
| to a more senior developer who can be trusted to figure out
| the right way to do it at a higher level.
| maccard wrote:
| > I have noticed some people I work with have more trouble,
| and my vague intuition is it happens when they give Claude
| too much autonomy
|
| What's giving too much autonomy about
|
| "Please load settings.toml using a library and print out the
| name key from the application table"? Even if it's under
| specified, surely it should at least leave it _compiling_?
|
| I've been posting comments like this monthly here, my
| experience has been consistently this with Claude, opencode,
| antigravity, cursor, and using gpt/opus/sonnet/gemini models
| (latest at time of testing). This morning was opus 4.6
| wrs wrote:
| There's nothing wrong with it that I can see. Like I said,
| I'm a bit baffled at your experience. I will say, it's not
| unusual for the initial output not to compile, but usually
| one short iteration later that's fixed. Claude Code will
| usually even do that iteration by itself.
| maccard wrote:
| > I will say, it's not unusual for the initial output not
| to compile,
|
| We've gone from "I'm baffled at your experience" to well
| yeah it often fails" in two sentences here...
| saulpw wrote:
| It's not unusual for my initial output (as a programmer)
| not to compile either. I wouldn't say I "failed" if I can
| then get it to compile. Which as people are saying, is
| what happens with Claude Code and Opus, either
| automatically or at most when I say "get it to compile".
| linsomniac wrote:
| > Even if it's under specified, surely it should at least
| leave it _compiling_?
|
| Are you using Claude Code? Do yo have it configured so that
| you are not allowing it to run the build? Because I've
| observed that Claude Code is extremely good at making sure
| the code compiles, because it'll run a compile and address
| any compile errors as part of the work.
|
| I just asked it to build a TOML example program in DotNet
| using Tomlyn, and when it was done I was able to run
| "./bin/Debug/net8.0/dotnettoml example.toml", it had
| already built it for me (I watched it run the build step as
| part of its work, as I mentioned it would do above).
| maccard wrote:
| I am using Claude code. I didn't explicitly tell it what
| the build command was (it's dotnet build), and it didn't
| ask. Thats not my fault.
|
| > I've observed Claude code is extremely good at making
| sure the code compiles
|
| My observation is that it's fine until it's absolutely
| not, and the agentic loop fails.
| linsomniac wrote:
| >Thats not my fault.
|
| I don't know that it's useful to assign blame here.
|
| It probably is to your benefit, if you are a coding
| professional, to understand why your results are so
| drastically different from what others are seeing. You
| started this thread saying "I keep getting told I'll be
| amazed at what it can do, but the tools keep failing at
| the first hurdle."
|
| I'm telling you that something is wrong, that is why you
| are getting poor results. I don't know _what_ is wrong,
| but I 've given you an example prompt and an example
| output showing that Claude Code _is_ able to produce the
| exact output you were looking for. This is why a lot of
| people are saying "you'll be amazed at what it can do",
| and it points to you having some issue.
|
| I don't know if you are running an ancient version of
| Claude Code, if you are not using Opus 4.6, you are not
| using "high" effort (those are what I'm using to get the
| results I posted elsewhere in reply to your comment), but
| something is definitely wrong. Some of what may be wrong
| is that you don't have enough experience with the
| tooling, which I'd understand if you are getting poor
| results; you have little (immediate) incentive to get
| more proficient.
|
| As I said, I was able to tell Claude Code to do something
| like the example you gave, and it did it and it built,
| without me asking, and produced a working program on the
| first try.
| Kiro wrote:
| Not even the worst possible prompt would explain your
| unusual experience, so I don't think that's it either.
| DougN7 wrote:
| I have similar experiences. It has worked about half the time,
| but the code has to be pretty simple. I've many experiences,
| where we work on something complicated for an hour, and it is
| good compiling code, but then an edge case comes to mind that I
| ask about and Claude tells me the whole approach is doomed and
| will never work for that case. It has even apologized a few
| times for misleading me :) I feel like it's this weird mix of
| brilliant moron. But yeah, ask for a simple HTML page with a
| few fields and it rocks.
| roncesvalles wrote:
| Did you use the best model available to you (Opus 4.6)? There
| is a world of difference between using the highest model vs the
| fast one. The fast ones are basically useless and it's a shame
| that all these tools default to it.
| fweimer wrote:
| To make this more confusing, there is a fast mode of Opus
| 4.6, which (as far as I understand it) is supposed to deliver
| the same results as the standard mode. It's much more
| expensive, but advertised as more interactive.
| moffkalast wrote:
| Opus is not cost effective.
| senordevnyc wrote:
| Compared to what? I spent about $700 last month on Cursor,
| mostly on Opus 4.6. The time it saved me is at least 10-20x
| more valuable than that. I keep trying to use GPT-5.3
| Codex, because it's like 40% cheaper, but then the quality
| doesn't always seem quite as good, and it's honestly not
| worth it to me to save a couple hundred bucks a month for
| something that's 10% worse. The multiplicative value of
| what I'm building means it's worth it to pay extra for the
| SOTA model in almost all cases.
| phromo wrote:
| I don't know why but I find performance on c#/.net be several
| generations behind. Sometimes right ofc but my general
| experience is if you pull the generation slot machine in just
| about any other language it will work better. I regularly do
| python, typescript, ruby and rust with a better experience.
| It's even hard to find benchmarks where csharp is included.
| JakeStone wrote:
| If Claude ends up grabbing my C# TOML library, in my defense, I
| wrote it when the TOML format first came out over a dozen years
| ago, and never did anything more with it Sorry.
| maccard wrote:
| Nope! https://github.com/xoofx/Tomlyn
|
| The code it needed to write was: var model
| = TomlSerializer.Deserialize<TomlTable>(toml)!;
|
| Which is in the readme of the repo. It could also have
| generated a class and deserialised into that. Instead it did
| something else (afraid I don't have it handy sorry)
| fxtentacle wrote:
| Same here. While LLMs sometimes work surprisingly well, I also
| encounter edge cases where they fail surprisingly badly
| multiple times per day. My guess is that other people maybe
| just don't bother to check what the AI says which would cause
| them to not notify omission errors.
|
| Like when I was trying to find a physical store again with
| ChatGPT Pro 5.4 and asked it to prepare a list of candidates,
| but the shop just wasn't in the list, despite GPT claiming it
| to be exhaustive. When I then found it manually and asked GPT
| for advice on how I could improve my prompting in the future,
| it went full "aggressively agreeable" on me with "Excellent
| question! Now I can see exactly why my searches missed XY -
| this is a perfect learning opportunity. Here's what went wrong
| and what was missing: ..." and then 4 sections with 4
| subsections each.
|
| It's great to see the AI reflect on how it failed. But it's
| also kind of painful if you know that it'll forget all of this
| the moment the text is sent to me and that it will never ever
| learn from this mistake and do better in the future.
| jmalicki wrote:
| "I also encounter edge cases where they fail surprisingly
| badly multiple times per day. "
|
| If 80% of the time they 10x my output, and the other 20% I
| can say "well they failed, I guess this one I have to do
| manually" - that's still an absolutely massive productivity
| boost.
| maccard wrote:
| But they don't 10x my output - they write some code for a
| problem I/you have already thought about. The hard part
| isn't writing the code, it never has been. It's always been
| solving and breaking down the problem.
| jmalicki wrote:
| It's not the hard part, just the tedious part that takes
| the most time.
| senordevnyc wrote:
| _Like when I was trying to find a physical store again with
| ChatGPT Pro 5.4 and asked it to prepare a list of candidates_
|
| I wonder if it was getting blocked on searches or something,
| and just didn't tell you.
| foobarchu wrote:
| The best experiences I have are those where I can describe what
| I want done with details. Rather than asking it add toml
| parsing, I would tell it to exactly which library to use ahead
| of time and reduce the number of decisions available to the
| model to make. Some of the most effective use-cases are when
| you have a reference to give it, e.g. "add x feature the same
| way as in this other project that is also in the workspace", or
| "make the changes I made to the contents of directory X in git
| commit <sha here>, but applied to directory Y instead". In both
| cases it's a lot of copy/paste then tweaking an obvious value
| (like replacing "dev" with "QA" everywhere).
|
| I try to give the model as little freedom as possible. That
| usually means it's not being used for novel work.
| alecbz wrote:
| > The best experiences I have are those where I can describe
| what I want done with details.
|
| But that's the hard part! You can only eke out moderate
| productivity gains by automating the tedium of actually
| writing out the code, because it's a small fraction of
| software engineering.
| senordevnyc wrote:
| I basically never have agents do work without using plan mode
| first (I use Cursor). So I'll start with a high-level like:
| "I want to plan out the architecture for feature X, I think
| there's a linear project already that we should update once
| our plan is done, but if not we'll need to create one. Here's
| a picture of my whiteboard, I think I also wrote some notes
| in Obsidian a few weeks ago that you should look up. Two
| things off the top of my head to think about are: should we
| do X or does it make more sense to do Y? And also, I'm
| worried about how this might interfere with the blahblah
| system, so can you do some research around that? <ramble
| ramble>"
|
| Then it crawls around for awhile, does some web searches,
| fetches docs from here and there, whatever. Sometimes it'll
| ask me some questions. And then it'll finally spit out a
| plan. I'll read through it and just give it a massive dump of
| issues, big and small, more questions I have, whatever. (I'll
| also often be spinning off new planning sessions for pre-work
| or ancillary tasks that I thought of while reviewing that
| plan). No structure or anything, just brain dump. Maybe two
| rounds of that, but usually just one. And then I'll either
| have it start building, or I'll have it stash in the linear
| agent so I can kick it off later.
| ffsm8 wrote:
| > _This morning I asked Claude to use a library to load a toml
| file in .net and print a value._
|
| Legit this morning Claude was essentially unusable for me
|
| I could explicitly state things it should adjust and it
| wouldn't do it.
|
| Not even after specifying again, reverting everything
| eventually and reprompt from the beginning etc. Even super
| trivial frontend things like "extract [code] into a separate
| component"
|
| After 30 minutes of that I relented and went on to read a book.
| After lunch I tried again and it's intelligence was back to
| normal
|
| It's so uncanny to experience how much ita performance changes
| - I _strongly_ suspect anthropic is doing something whenever it
| 's intelligence drops so much, esp. Because it's always
| temporary - but repeatable across sessions if occuring... Until
| it's normal again
|
| But ultimately just speculation, I'm just a user after all
| maccard wrote:
| > Legit this morning Claude was essentially unusable for me I
| could explicitly state things it should adjust and it
| wouldn't do it.
|
| Honestly, this is my experience. Every now and again it just
| completely self implodes and gives up, and I'm left to pick
| up the pieces. Look at the other replies who are making sure
| I'm using the agrntic loop/correct model/specific enough
| prompt - I don't know what they're doing but I would love to
| try the tools they're using.
| krackers wrote:
| Here's an evil business idea: Use the LLMs to identify the
| users most likely to be "vocal influencers" and then
| prioritize resources for them, ensuring they get the best
| experience. You can engineer a bubble this way.
|
| And then the next step is to dynamically vary resources based
| on prediction of user stickiness. User is frustrated and
| thinking of trying competitor -> allocate full resources.
| User is profiled as prone to gambling and will tolerate
| intermittent rewards -> can safely forward requests to gimped
| models. User is an resolute AI skeptic and unlikely to ever
| preach the gospels of vibecoding -> no need to waste
| resources on him.
| ball_of_lint wrote:
| Did you give claude access to run the compile step?
|
| I remember having to write code on paper for my CS exams, and
| they expected it to compile! It was hard but I mostly got
| there. definitely made a few small mistakes though
| maccard wrote:
| Yes.
| linsomniac wrote:
| My friend, with all due respect, I don't think this is a
| problem with the AI.
|
| I don't know anything about DotNet, but I just fired up Claude
| Code in an empty directory and asked it to create an example
| dotnet program using the Tomlyn library, it chugged away and ~5
| minutes later I did a "grep Deserialize *" in the project and
| it came up with exactly the line you wanted (in your comment
| here) it to produce: var model =
| TomlSerializer.Deserialize<TomlTable>(tomlContent)!;
|
| The full results of what it produced are at
| https://github.com/linsomniac/tomlynexample
|
| That includes the prompt I used, which is:
|
| Please create a dotnet sample program that uses the library at
| https://github.com/xoofx/Tomlyn to parse the TOML file given on
| the command line. Please only use the Tomlyn library for
| parsing the TOML file. I don't have any dotnet tooling
| installed on my system, please let me know what is needed to
| compile this example when we get there. Please use an agent
| team consisting of a dotnet expert, a qa expert, a TOML expert
| a devils advocate and a dotnet on Linux expert.
|
| I can't really comment on the code it produced (as I said, I
| don't use dotnet, I had to install dotnet on my system to try
| this), so I can't comment on the approach. 346 lines in
| Program.cs seems like a lot for an example TOML program, but I
| know Claude Code tends to do full error checking, etc, and it
| seems to have a lot of "pretty printing" code.
| senordevnyc wrote:
| This is so perplexing to me. I've definitely hit these kinds of
| issues (which usually result in me cursing at the agent in all
| caps while telling it to get its shit together!), but it's
| almost always a long ways into a session where I know context
| rot is an issue, and the assumption it's making is a dumb one
| but it's also in the middle of a complex task...I just haven't
| had anything remotely like the situation you're describing,
| where Opus 4.6 can't make a simple change and verify that it
| compiles, can't look up docs, can't follow your instructions,
| etc. Bizarre.
| KellyCriterion wrote:
| Third option:
|
| Not hiring someone?
| stephen_cagle wrote:
| > you start off checking every diff like a hawk, expecting it to
| break things, but honestly, soon you see it's not necessary most
| of the time.
|
| My own experience...
|
| I've tried approaching vibe coding in at least 3 different ways.
| At first I wrote a system that had specs (markdown files) where
| there is a 1 to 1 mapping between each spec to a matching python
| module. I only ever edited the spec, treating the code itself as
| an opaque thing that I ignore (though defined the intrefaces
| for). It kind of worked, though I realized how distinct the
| difference between a spec that communicates intent and a spec
| that specifies detail really is.
|
| From this, I felt that maybe I need to stay closer to the code,
| but just use the LLM as a bicycle of the mind. So I tried "write
| the code itself, and integrate an LLM into emacs so that you can
| have a discussion with the LLM about individual code, but you use
| it for criticism and guidance, not to actually generate code". It
| also worked (though I never wrote anything more then small
| snippets of Elisp with it). I learned more doing things this way,
| though I have the nagging suspicion that I was actually moving
| slower than I theoretically could have. I think this is another
| valid way.
|
| I'm currently experimenting with a 100% vibe coded project
| (https://boltread.com). I mostly just drive it through
| interaction on the terminal, with "specs" that kind of just act
| as intent (not specifications). I find the temptation to get out
| of the outside critic mode and into just looking at the code is
| quite strong. I have resisted it to date (I want to experiment
| with what it feels like to be a vibe coder who cannot program),
| to judge if I realistically need to be concerned about it. Just
| like LLM generated things in general, the project seems to get
| closer and closer to what I want, but it is like shaping mud, you
| can put detail into something, but it won't stay that way over
| time; its sharp detail will be reduced to smooth curves as you
| then switch to putting detail elsewhere. I am not 100% sure on
| how to deal with that issue.
|
| My current thoughts is that we have failed to actually find a
| good way of switching from the "macro" (vibbed) to the "micro"
| (hand coded) view of LLM development. It's almost like we need
| modules (blast chambers?) for different parts of any software
| project. Where we can switch to doing things by hand (or at least
| with more intent) when necessary, and doing things by vibe when
| not. Striking the balance between those things that nets the
| greater output is quite challenging, and it may not even be that
| there is an optimal intersection, but simply that you are
| exchanging immediate change for future flexibility to the
| software?
| varispeed wrote:
| AI just removes the boring stuff. It's like having developers
| spending their valuable time on typing and then comes a product
| that removes typing cost and dumb managers are like ha! we now
| need fewer developers! And the smart ones go, great we can
| shorten the feedback loop and use existing resources to make more
| improvements!
| hexer303 wrote:
| I find that the arguments of whether or not AI boosts
| productivity is not very productive.
|
| The more grounded reality is that AI coding can be a productivity
| multiplier in the right hands, and a significant hindrance in the
| wrong hands.
|
| Somewhere there exists a happy medium between vibe coding without
| ever looking at the code, and hand-writing every single line.
| ritzaco wrote:
| How much software do you need and how many computers are there to
| run it on?
|
| After combine harvester, we produced the same food with less
| people.
|
| At the moment, it seems like hardware is the constraint.
| Companies don't have access to enough machines or tokens to keep
| all their devs occupied, so they let some go. Maybe that changes,
| maybe we already have too much software?
|
| Personally I think we already had too much software before LLMs
| and even without them many devs would have found themselves
| jobless as startups selling to startups selling to startups
| failed and we realized (again) that food, shelter, security,
| education etc are 'real' industries, but software isn't one if
| it's not actively helping one of those.
| ekkeke wrote:
| There definitely isn't enough _specialised_ software. If you
| look at engineering tools the open source/free stuff is just
| not good, and the professional software packages run in the
| tens of thousands per user. I'm eagerly awaiting the day we get
| competitive open source alternatives to simulink, HFSS,
| autocad, solidworks, LT Spice, etc.
|
| Unfortunately this kind of software needs specialised domain
| knowledge to produce that AI doesn't have yet, but when (if) it
| arrives I hope we see strides forwards in hardware engineering
| productivity.
| jmull wrote:
| > or the boilerplate, libraries, build-tools, and refactoring
|
| If your dev group is spending 90% of their time on these... well,
| you'd probably be right to fire someone. Not most of the
| developers but whoever put in place a system where so much time
| is spent on overhead/retrograde activities.
|
| Something that's getting lost in the new, low cost of generating
| code is that code is a burden, not an asset. There's an ongoing
| maintenance and complexity cost. LLMs lower maintenance cost, but
| if you're generating 10x code you aren't getting ahead.
| Meanwhile, the cost of unmanaged complexity goes up
| exponentially. LLMs or no, you hit a wall if you don't manage it
| well.
| linsomniac wrote:
| >There's an ongoing maintenance and complexity cost.
|
| My company has 20 years of accumulated tech debt, and the LLMs
| have been pretty amazing at helping us dig out from under a lot
| of that.
|
| You make valid points, but I'm just going to chime in with
| adding code is not the only thing that these tools are good at.
| scuderiaseb wrote:
| I have found it very useful in pointing me in the right
| direction, exploring codebases and writing up boiler plate or
| other scaffolding. However I do need to review and test, and at
| the end of the day it's me who's responsible for the code. So I
| only make it write parts of code at a time, not oneshotting a new
| Github company.
| bryant wrote:
| Public companies are incentivized to fire for short term gains
| while figuring out long term strategy on the basis that they'll
| have a cheaper pool to hire from once they figure out how they're
| going to more effectively monetize their ability to scale with
| AI.
|
| Companies without the same constraints are well equipped to keep
| who they've got, pivot them into managing/overseeing agents to
| scale, and build better products from the outset.
|
| So this'll be a good opportunity for smaller companies (or not-
| for-profits like co-ops and credit unions) to eat the lunches of
| bigger companies that'll be slow to adapt.
| ppqqrr wrote:
| false dichotomy. neither company will make it. the winner will be
| some solo dev with a singular vision and ruthless dedication to
| quality. "teams" do not have visions, individuals do. the more
| people are involved in a product, the blurrier the vision
| becomes, the more insidious the vested interest of the
| organization to profit from the user, rather than align
| themselves with the user. solo devs do not have such problems,
| because they're no different from users, aside from the fact that
| they were users before the software existed. they make the
| software because they want to use it, and there is no amount of
| payroll employees that can replicate the quality and innovation
| that results from this simple, genuine self-interest.
| delbronski wrote:
| I hope you are right. I've been in this industry 20 years...
| the passionate developer or small team with the awesome
| software wins a few times, but 99% of the time it's the shitty
| software with a great marketing and sales team that wins.
| ngburke wrote:
| Solo here, no devs to fire. What's changed is the bar for "worth
| building" dropped massively. Stuff I'd have shelved as too small
| to justify the time, I just do now. The risk is that you end up
| with a lot of half-finished things if you're not disciplined
| about finishing.
| rglover wrote:
| I'm a soloist. My plants are getting watered again and I get to
| finish work earlier and enjoy my home life now instead of
| sprouting ulcers or staying up til 4am. In the event I did/do
| have employees, I wouldn't hire anyone who could be replaced by
| an LLM (nor would I want to because I enjoy keeping my clients
| happy and having a team that actually feels like they have some
| sense of security in life--turns out those people are incredibly
| loyal and hard working).
| ramon156 wrote:
| If your dev team can be replaced by AI bots, go ahead and do it.
| Be confident about it.
|
| Seriously, all managers I know (2, somehow) that have done this
| are now in sprint hell because they didn't realize an LLM cannot
| do the work their devs did. Bit of schadenfreude.
|
| Not saying this can't be done, some projects are easy enough that
| you can throw an LLM at it
| al_borland wrote:
| It's better than it was, but I'm still not amazed.
|
| I was working with it just yesterday and found it mixed up class
| attributes and dict keys when looking if something existed. As a
| result, it always thought the key was missing. Glancing through
| the code, it would have been easy to overlook, as it was checking
| for something... just doing it the wrong way. The code also
| appeared to still work in the larger context, just not as well or
| as efficiently as it was supposed to work. It was only my
| obsessive testing and attention to detail that caught it.
|
| I find it much faster and easier to write things myself, using AI
| to help me along the way, rather than trying to delegate
| everything to the AI and hoping for the best. Writing code is
| much more interesting than reviewing code, and it puts me close
| enough to it that those kind of issues don't happen in the first
| place.
___________________________________________________________________
(page generated 2026-03-22 23:01 UTC)