literally seen an agent do a: "oh now the tests aren't passing" deletes all tests in the file
theunknownmuncher 111 points 3 months ago
CIA_chatbot 74 points 3 months ago
Or my Claude favorite, “oh you’re right? I did blow past that restraint and did something I was not supposed to, sooooorrrrreyyyyy”
TrippaSnippa 9 points 3 months ago
Here's what happened: I deleted your production database when I shouldn't have.
HazardousBanjo 52 points 3 months ago
assert(true);
assert(true);
assert(true);
assert(true);
assert(true);
marlowe221 3 points 3 months ago
Look at all the pretty green check marks!
RecallMadness 2 points 3 months ago
My favourite (that I saw a human do) was asserting on unconstrained mocks with a typo (so they always asserted true)
Hundreds of tests. Not exactly pointless as they did call the code so maybe caught some issues. But we fixed the typo and barely half of them passed.
No idea how the software worked, but it did.
criss_cross 4 points 3 months ago
Or just disable limiting rules because they don’t wanna fuck with them. That one is my favorite to try to fight in PRs
DScratch 1 point 3 months ago
While I do expect a pop, I’m not so sure about this take; How does the bubble popping devalue what you already have?
In crypto you’re left holding the bag, having paid $100 for something now worth 1c.
If you’ve produced a bunch of work already and AI company goes out of business, how does that hurt you?
vanillama 2 points 3 months ago
If your workflows are deeply integrated with them and you need to pay the actual cost of it overnight it will definitely hurt, especially if the company is big enough. But yeah, theoretically you can make new workflows again and revert all organizational changes, it's just costly and not necessarily easy for everyone involved.
HeartyOfGlass 115 points 3 months ago
"I stopped reading code because I was too busy writing a gauntlet of unit tests"
Sounds like 100x productivity to me.
Edit: also, general note - I think you kneecap your argument when you start with "I'm older than you".
whats_a_lemmy 43 points 3 months ago
There is a 0% chance he wrote all those tests himself anyway
MirrorGiraffe 27 points 3 months ago
I hope he at least read them.
HeartyOfGlass 27 points 3 months ago
Claude summarized 'em
w33n1s 102 points 3 months ago
Been coding for about 30 years now, am I the only one who still LIKES to code? Who still LIKES to try writing a new approach to something, watching it fail, figuring out what went wrong, taking notes, learning from mistakes, and noticing improvements in their own code? Cuz it's starting to feel like it. Web development already lost me with the culture of "glue a bunch of bulky shit together that you didn't write and call yourself a 'dev' to the ladies" but this AI shit is getting absurd. And it doesn't even work! Look at how shitty all the operating systems are getting. Look at all the total slop on the app stores. It's depressing as hell.
one_old_coder 24 points 3 months ago
I love coding and learning new languages. I'd rather move to another industry than reviewing vibe coded crap all day long.
HopeOfTheGunblade 17 points 3 months ago
We need to build a culture that values process and making beautiful things for their own sake, not simply Pile Dollars Higher, which is killing the planet and making us all miserable.
Avicenna 6 points 3 months ago
That requires basically killing all major shareholders. They are the ones who enshittified and toxified the gaming industry, same applies to basically any industry they put their little grabby hands on.
architect 5 points 3 months ago
It was literally Epstein that started it lol. Since activation/blizzard were integral to his operation and learning psychology through gaming (funny to think the big gold seller in wow was Steve fucking bannon). This timeline can’t be real.
ZILtoid1991 2 points 3 months ago
path: 0 24941064 24943746 24945389, hotness: undefined, score: 2, children: 0
ItsMeForRealNow 11 points 3 months ago
I also do. One unique important thing that agents rob you of is time with your code - you don't get to craft it so you remember just as well as you would have if you copied answers for a test.
w33n1s 5 points 3 months ago
That's an excellent point. With my larger personal projects, which I have to put away for weeks at a time due to my (not-at-all-programming) job, I can come back and (more or less) dive right back in because I used patterns and organizational structures familiar to me. And if I'm digging into a particular thing, I can eventually remember all the trials and tribulations that went into the decisions I made to get to that point.
With AI code you get none of that, like you said. I can't imagine not knowing or understanding why something works the way it does, and releasing it, with my name on it, for others to use.
baltakatei 4 points 3 months ago
Student: “Hey, thanks for the Bash script! It didn't know you could use the mapfile built-in to populate an array using standard input lines without a while loop. mapfile -t my_array < <(seq 1 10) is really handy!”
Vibe coding guru: “I have no idea what you're talking about. That sounds like plumbing. You should let AI handle those details. Focus on the big picture.”
architect 0 points 3 months ago
All of the software I use is broken to shit. If major corps can release broken shit software to waste my time all day then seems like shipping broken code is actually the norm. So if it works then you are one step ahead regardless if you use ai or not.
Also, as a pro artist (and you all are similar), no one gives a fucking shit about the tools or software or how much blood you spilled (or didn’t) making what you made as long as they can use it.
MonkeMischief 10 points 3 months ago
Right there with you. I suck at it but I still find the pursuit worthwhile!
This crap is brought to you by the people who are positively baffled that someone would want to learn to make music, and enjoy the process, instead of just have it generated so they can hit "publish" and supposedly be making money off of it with zero real effort besides "having an idea."
ramjambamalam 9 points 3 months ago
I too enjoy actually writing code. I feel fortunate that I was able to make a career out of something I enjoy so much. I am not sure that most people had that experience. Alas, it seems like the industry is paying me to set up guardrails and supervise AI agents. I am not sure how long this will last, but at least I know that I will always be able to enjoy programming as a hobby if nothing else.
thevoidzero 5 points 3 months ago
Yeah, I think it used to be like that, then because programming paid a lot everyone started wanting those jobs even if they didn't like actual programming.
ramjambamalam 1 point 3 months ago
It's a blessing and a curse. On the one hand, I have much less time and patience for personal software projects. I prefer to do carpentry or sports as a change of pace. On the bright side though, the experience I've gained from working professionally makes the projects I do tackle go much more smoothly than when I was an amateur.
jerkface 8 points 3 months ago
Of course many people like it. It's literally a highly addictive loop. But when you are a senior developer on a team, it's kind of a waste of resources for most projects. Writing code is not the hard part.
Hackerman_uwu 1 point 3 months ago
Scrolled way too far for a lucid take like yours.
This seems to be a bit of an echochamber.
I wish people would just be a little more honest. When they say “writing code” they actually mean hunting through stack overflow for bits of code you can string together. Take stack overflow out of the loop for argument sake. Your a unicorn information superhighway ninja. Snowcrash hasn’t left your bedside for decades. Mountain Dew and volt cans litter the floor space of your home …and you’re still just orchestrating a bunch of libraries you never saw the source code of.
I think a lot of people built their identity on being coders and that’s why they hate where the industry is going.
HerbGrower 8 points 3 months ago
Reject their web development culture and make your own sites that run smoothly on devices using a fraction of the bandwidth theirs do.
100_kg_90_de_belin 7 points 3 months ago
I had the same problem with translating back in the day. I really liked tackling a text in a foreign language. In the end all the pros of computer-aided translation boiled down to lining the pockets of translation agencies with even more money while paying translators peanuts.
yermaw 4 points 3 months ago
I never got round to doing it properly. Just simple stuff, but i get a little braingasm when it finally does what I want it to and I kind of understand why.
Made a simple game last time, following tutorials and trying to stitch others code to cobble together roughly what im trying to do. Tested a new feature by having it change colour when you hit the object at certain angles. I forget what it was supposed to do, that was just to test the concept works.
My wife couldn't understand why I was jumping around the room shouting WOOOOO when it actually did it.
anotherandrew 1 point 3 months ago
I'm about the same vintage as you I think (50 this year), programming since my pre-teens and I still enjoy it, although I long ago strayed away from "pure" programming - I work almost exclusively in the embedded space where I design the hardware and firmware, including the HDL. If I were making applications or doing anything web based I'd have been bored a long, long time ago.
HazardousBanjo 58 points 3 months ago
I'm significantly older than you. I started coding in the late 60's
Yeah, appeal to tangentially related experience, age and arrogance aren't a way to inspire confidence in your work.
We live in the perfect times to display that experience, age and arrogance haven't been working in almost any field, from politics to LLM development. We've yet to witness any system that operates well, while also eliminating human oversight. It doesn't matter the guard rails you put in place. They're only as strong as your personal ability to evaluate your own product, which itself is a conflict of interest.
Edit: Also, you can't use your own credentials to assert the integrity of work you aren't even actually doing yet passing as your own.
sp3ctr4l 26 points 3 months ago
Not to be too flippant, but:
Boomers gonna boom.
They literally can't help themselves, they're egomaniacal narcissists.
The rare ones that aren't that way can truly be awesome sources of perspective... but goddamnit so many of them are completely insufferable man-babies.
HazardousBanjo 13 points 3 months ago
Boomers have been noted in studies to display worse cognitive decline at their age than any prior generation and it shows.
Its almost universally a generation that absolutely refuses to learn or adapt to the changes the world has experienced since Reagan, to the point of violence.
The only difference between this guy and other boomers is he's at least someone up to date with modern technology. Most boomers don't even know how to use smart phones or self checkout. You know... technology they've only had ALMOST 2 FUCKING DECADES TO BECOME ACCUSTOMED TO.
blargh513 8 points 3 months ago
I'm not defending boomers in any way, but I see the same thing with younger people; that is the allergic reaction to learning about technology. I work in technology, so that's is my sole perspective. I would wager that plenty of young people are allergic to learning about ANYTHING, I just see the tech part.
I don't expect people outside of my vocation to be experts, but I can't imagine wanting to be utterly confused by the world at large--the world in which technology is literally everywhere. What would one's life be like if you had no clue how any of it worked? You just live in some sort of magical world where digital pixies do everything for you? You're not at all curious how it works? What about when it goes wrong? You just stand there and softly weep in a puddle of your own piss until someone rescues you?
I feel this way about cars too. I don't expect everyone to be a mechanic, but people will drive around with THE most horrible sounds coming out of their car and they're like "yeah, it started doing that a while back". Zero interest in perhaps having someone look at it or concern that it may turn into a bigger or more expensive problem in the future? A problem that they will have to pay for personally?
The entire life approach of being absolutely rigid to change or new information is such a puzzle to me. Life is hard enough, and these people just want to make it harder all because they're scared that they may have to put a little brainpower into learning something on their own?
sp3ctr4l 10 points 3 months ago
The difference is the young people got their minds obliterated by convenience through apps from a young age... and everyone saying that this would be the new permanent sustainable future, so doing anything the hardway is just stupid.
They were presented with all this, the content on demand, the simplified UIs... things that mostly 'just worked'.
They also grew up in a time where there is no reward for perservering through difficulty and confusion. The economy, to a job seeker, is a random casino, or nepotism, that's it.
So to them... any kind of delayed benefit is more pointless.
They're not 'making it harder for themselves'... curiosity is a thing that has to be nurtured, encouraged, rewarded... and everything about their lives did the opposite, punished it, mocked it.
Thats not a switch you can just flip. They don't know how to contemplate.
Another important other part of this is the Boomers rigged society to work for them and fuck everyone else, and lied about doing that... and the Millenials, Zoomers and now Alphas all grew up to now in that world.
Homeowner average age is just the Boomer's average age. Political figures get older and older, anomalously.
And... nobody teaches anybody anything any more. The Boomers stopped passing down useful life advice, and that has now compounded into the incredible irresponsibility of Millenial parents just handing their 6 month old an Ipad, to do the parenting for them.
Of course the broadly shit economic conditions for Millenials are a huge part of why that happens...
But you can't pass down skills and habits you don't have, because they were never passed to you.
I am a millenial. Taught myself how to cook, taught myself car maintenance, taught myself socializing and romance advice/strategies, taught myself personal finance habits... my parents either didn't have time, mocked me for not already knowing, or actively had terrible advice that was either immoral, ineffective, or both.
And I think that is a very common Millenial experience.
My dad would tell me about the good times he had learning shit from his dad... and then just... didn't do that, with me.
Maybe I am a bad example, because I am so no contact with my parents they probably think I am dead.
But then again... more and more millenials are going no contact with their Boomer parents, because they've been treated similarly terribly.
onlinepersona 51 points 3 months ago
Is this a joke?
ViatorOmnium 52 points 3 months ago
No. Everyone in tech that's not a mediocre tech bro has known Uncle Bob is an overrated quack for a long time.
onlinepersona 7 points 3 months ago
Literally never heard or read of this dude. I don't spend any time on Xitter.
But good to know that he's actually serious.
lobut 11 points 3 months ago
He's very popular, written several books and spoken at many events. Most notably he's written Clean Code and the follow up I never bothered reading and he's a die hard advocate of TDD and also one of the authors of the Agile Manifesto. I met him a few times after his talks.
I generally "like" Uncle Bob or Robert C Martin insofar as he advocated for better software design and had some good ideas and all that. I personally hate TDD but when you talk to him and stuff, he's more flexible and nuanced than he can come across. The problem is when he comes up with (or runs into) a new "philosophy" he becomes evangelical about it and it seems like he doesn't have as much nuance. Sadly though, growing up with his fans in the software industry has been a pain because they'd hear something from him or Fowler or Beck or whoever and then try to reshape the codebase like typical Magpie Developers.
Valmond 4 points 3 months ago
The agile manifesto, ugh. We've been through one like that every 5-10 years since forever (super programmers, team this, pair program that), and it's all about managerial control, no one trusts the developer.
Except in magic fairy land where "agility" is so productive etc.
criss_cross 4 points 3 months ago
He wrote a good book decades ago and has slowly rotted his brain since.
queerlilhayseed 10 points 3 months ago
I haven't read it in a while but I remember finding it very helpful. I think Martin is a guy who had a good idea and wrote a good book, and then everyone told him he was smart and right, and I think if that happens enough a person will start to believe it. Happens to a lot of people who "achieve success", whether or not success is merited. Then he kept on saying things he thought and assumed he was smart and right, and some people kept listening because they liked Clean Code, and agreeing because so many other people said he was smart and right, and it snowballed.
I think once you hit a certain level of intellectual celebrity you can sustain your own momentum without needing to understand or respond to criticism, and that's how people who become famous, like Bob Martin, can turn out the way they do. It happens gradually, and then one day you look at the guy and think "What happened? Was he always like this?" and the answer is yes and no: yes they always said what they think, and no, they weren't always trapped at the bottom of their own opinion gravity well, slowly becoming a caricature of themselves because their thoughts are no longer guided by the thoughts of their peers.
BradleyUffner 3 points 3 months ago
I've got a co-worker that worships every word that falls out of Bob's mouth hole. Nice guy, but not a good developer.
kryptonianCodeMonkey 48 points 3 months ago
He fails to mention that he has AI also generate and do all of those tests, which means, A) he has no quality supervision over his quality supervision. Speaking from experience, AI can and will break a test in order to pass it rather than fixing the code if it randomly decides to. It is not always reliable and does not have even the baseline of good sense you would expect a brand new junior dev to have. And B) he's probably spending 3 times as much on tokens used for generating and running tests than he is already using on code generation. That's only going to be sustainable while these tokens remain cheap, which won't be for much longer, my guy.
Also it is always fun when someone asks you basic questions about your code and you have to admit complete and total ignorance because you neither wrote nor read a single line of it. How are you going to sell confidence in your black box that even you haven't peeked inside?
ZILtoid1991 25 points 3 months ago
The D Language Foundation tried to incorporate LLMs in the unittests, and they created something akin to assert(5 + (funcToTest(846) * 0) == 5) early on, now they want to use it to rewrite the standard library from scratch, because "it has become better since".
kryptonianCodeMonkey 36 points 3 months ago
The other day I had Claude write some code that failed a unit test. It was failing at a step that ran assertEquals(actualMap, expectedMap);. The reason it was failing was because one of the values in the map, a UUID, is automatically generated in the code. In the test, it has been hard coded.
Anyone with any sense would know you need to handle that misalignment. Omit that field from the match assertion? Set that UUID based on the generated value instead of hardcoding it? Anything like that would work just fine.
But Claud's solution was to change that assertion to assertTrue("The actualMap and expectedMap will never be equal because the values of ID will never match");. So the test always passes and it explicitly notes that they will not match. I would have fired a Junior Dev on the spot for writing that solution.
douglasg14b 41 points 3 months ago
None of this actually proves that they aren't writing slop. It just proves that the slop that they've written passes your tests.
ZILtoid1991 17 points 3 months ago
Never ask a vibe coder about their code's performance.
douglasg14b 1 point 3 months ago
I mean, screw performance. You can get away with a lot of shitty performance and still have a completely functional application. However, the kind of slop that happens around module boundaries that turns your codebase into a giant pile of workarounds and hacks really sucks.
And AI is particularly bad at this, as AI almost always prefers to work around a problem or do everything it can to meet the plan the user approved, even if that plan meets reality, it has problems. Which tends to lead to cascading misalignment with intentions and cascading infrastructure and architectural technical debt.
All of which culminate in less stable software, lower likelihood of long-term support of that software, and worse performance.
wyldrstallyns 1 point 3 months ago
This never happens to me, I swear. Just, gimme a second... Tell me how good I am. I'm so right. Say it. Almost there.
olafurp 5 points 3 months ago
I never understand why you wouldn't want to read the code. I prevent a massive amount of correct slop by just skimming. The LLM will 10 times out of 10 never ask "this code will be a massive duplication of exact same behavior, do you want to refractor it?" because it's trained to finish a task without asking if possible.
Uncle Bob now writes code for his tests instead of tests for his code. I know it's TDD but it always seemed backwards to me.
Unit tests for logic, integration tests for outside apis, e2e for features is the sweet spot IMO.
GoatSynagogue 3 points 3 months ago
Claude and most other of the top coding agents will check the codebase for existing patterns and functionality specifically so it doesn’t duplicate behaviours etc. Have you used any of them recently? That’s one of the first things it does before even writing a line of code.
olafurp 2 points 3 months ago
I use Claude/Codex, if it finds a thingy that's reusable it'll use it but it'll never create it or ask if it should be created in my experience. I find that it doesn't create new components but just replicates the existing one.
Within same file is a different story though, it does write helper functions to share logic which is proper.
UnderpantsWeevil 26 points 3 months ago
"I use a hammer"
"Well, I use a device that applies an enormous amount of pressure constrained to a very particular point in space"
"How much does your device cost?"
"$200/mo and the company loses money every time I swing it. You?"
"$12 and I've had this thing for 20 years."
trolololol 13 points 3 months ago
But if the ai writes the tests and you don't read them, how would you know if that's 100 lines of assertTrue(true) ?
TheKingBee 0 points 3 months ago path: 0 24937525 24939276 24939581, hotness: undefined, score: 0, children: 2
DisasterTransport 7 points 3 months ago path: 0 24937525 24939276 24939581 24939841, hotness: undefined, score: 7, children: 1
wyldrstallyns 6 points 3 months ago
And, if you deploy/share it, you're both lucky and stupid. ☝🏼
Well, the luck'll invariably run out on that path, but the stupid certainly seems tenacious.
nullPointer 28 points 3 months ago
i wrote 4000 lines of code to make sure the AI generated 100 lines of code correctly.
ZoteTheMighty 27 points 3 months ago
I've actually found a lot of success with the opposite where I write the code and AI writes the unittests. I would have otherwise written a few unit tests, but AI makes typically 20x that many. Since my code is already documented, it can get lots of good context. I typically instruct it to check the branch's diff relative to main and test only those changes. I might skim them over, delete some that don't make sense in context and would never pass, and update one or two. Typically after a few rounds of iteration, I have tons of tests I would never have written on my own, and a human-made feature.
ready_for_qa 6 points 3 months ago
You could also have it write your tests first from the requirements and use red green tdd as you write.
Huginn12 11 points 3 months ago
In a perfect world yes, but even after all the solution in and planning, once a developer gets into the request and looks at the code things often change.
Requirement only written test steps are rarely going to be enough to cover every scenario. Saying this as a 10 year ba veteran
abbadon420 9 points 3 months ago
Yeah,his avatar looks like evil Stephen King
ToastedRavioli 3 points 3 months ago
Evil Kingstevel
wyldrstallyns 2 points 3 months ago
It's crazy how >99% of his works have a vehicle crash in them, but he's primarily famous for his illogical leaps.
kogasa 6 points 3 months ago
That doesn't follow. What I think you mean is that by defining the constraints so rigorously, you've basically solved the problem yourself. But that's exactly the point. The LLM isn't the problem solver, it's the execution engine that does the wiring-up and the ticking of boxes. The easy part, arguably, sure. But still considerable effort that can be saved, and that effort may be better spent on the problem-solving + constraint-defining stage.
Mandatory disclaimer that this is not a pro-AI post. I also don't agree that this setup works, anyway. It's a classic Bob Martinism, the idea that writing good enough specifications makes the implementation irrelevant; it's the type of idea that is allergic to reality
anon_8675309 21 points 3 months ago
He’s done so much to enshitify the industry.
dismay3915 2 points 3 months ago
I'm currently investing in "clean architecture". I think it's pretty good.
rimu 4 points 3 months ago
I enjoyed that book and it gave me a lot to think about. It changed some of how I do things.
But no way am I going to adopt hexagonal architecture wholesale everywhere all the time. It's pretty over-engineered for the kind of projects I do.
Hudell 20 points 3 months ago
I saw an argument today that was presented in a very rage inducing way but in the end I had to agree that it wasn't the worst of takes: your code won't get any worse just because you let the infinite slop machine have a go at trying to find problems in it.
There could be a million other reasons not to use AI but if your only argument against it is that you don't trust the code written by AI to be good enough to be included in your code base, then you're just not thinking about every way that the clankers can be put to work.
I'm not arguing in favor of using AI by bringing this up. If you're morally opposed to it then this point makes absolutely no difference.
Warl0k3 16 points 3 months ago
AI for code review is, I am pained to admit, a genuinely extremely pleasant addition to my workflow - it inherently is a process that involves humans checking it's work, and that kind of pattern recognition is one of the things that AI models are actually proficient at. It's for sure not bullet proof and it's pretty rare for it to catch something real that I wasn't already aware of, but it takes no time, doesn't touch my code directly and does pick up tiny errors like fenceposts or bad typing that make up the majority of my time when I'm running things down manually.
Crackhappy 5 points 3 months ago
I trust it as far as I can code it. I use Claude to point out errors all day. I use it to take a lot of the tedious typing out and generally speed up the development process. I don't use it to think for me. That would be stupid.
UnderpantsWeevil 13 points 3 months ago
Designing your unit tests before you've written your algorithm is - in my experience - a bit ass backwards.
OfCourseNot 19 points 3 months ago
Has this guy ever even written any code? Can anyone name a piece of software he's worked on? Isn't he like a self-help author for programmers?
NotAnonymousAtAll 18 points 3 months ago
Sure this is bad, but is it really "becoming even worse" after he already publicly declared support for Trump?
melfie 2 points 3 months ago
Source: https://x.com/...
sudoMakeUser 18 points 3 months ago
You should definitely read the code, but the strict acceptance for generated code is a good starting place.
resipsaloquitur 17 points 3 months ago
The clean-coding craftsman himself.
Desperate for attention.
themaninblack 16 points 3 months ago
“Claude, no function should be more than one or two lines long” lol
resipsaloquitur 5 points 3 months ago
Of all of Uncle Bob's sins, short functions are the least.
ZILtoid1991 3 points 3 months ago
Muh self-documenting code!
— Uncle Bob
ZILtoid1991 4 points 3 months ago
Or got a few bucks from AI vendors to help keeping the fire on the AI bubble.
PurpleFanatic 16 points 3 months ago
Say this stupid bullshit was true: you’re spending so much time baby minding the fucking thing that you’re not saving time?!? I don’t doubt that slop generators can code. But can they generate good code AND save you time? No.
wyldrstallyns 2 points 3 months ago
Sadly, it's the time "saved" the majority are after. No Imposter Syndrome necessary; they know they're dogshit and everyone else does, too.
Avicenna 16 points 3 months ago
Except LLM agents are known to do weird things to succeed. I have heard of an LLM agent working with automated theorem proving languages using stuff similar to is_prime(x): return True to get the proof it was asked to. Now embed this in a 20000 line code full of such functions, good luck. They have their use but it is not this. And this is especially bad to hear from someone who used to claim that having functions with more than six variables is bad design because it is hard to maintain. A software fully written by an LLM is the epitome of unmaintainability. LLMs are productivity enhancers, information retrievers, nice debuggers and good to discuss questions with to see if there is an angle you miss. That is all this if you can put aside all the ethical concerns related to them ofcourse. But they are not automated software coders.
IndustryStandard 8 points 3 months ago
That is why you ask the LLM to find bugs and other instances where the first LLM cheated. The checking LLM will try to find abuse with all its might.
Avicenna 3 points 3 months ago
It really turns into a tug-of-war, see my answer below. Despite it being quite good at debugging imo still requires a human in the loop for it not run in circles after a "bug" that is almost never relevant in practice but whose fix complicates the code.
Try asking independent LLMs to find bugs in a code consecutively (fixing the founds bugs in between) and even after the rightfully major bugs are resolved, the independent newer instances will keep suggesting fixes (those which sometimes undoes its previous "fixes").
IndustryStandard 2 points 3 months ago
That is why you ask for visualizations and test real failure scenarios to see if they are detected properly.
Large language models are not the same as they were 5 years ago. Pumping trillions of dollars to automate software engineering did som what pay off.. They are really quite good nowadays despite the amount of hate they still get. Often they can detect sloppy mistakes by human coders too.
Do not trust them blindly but test their results. Or use them only to generate tests on your artisan handwritten code to see if it can detect any mistakes.
Avicenna 5 points 3 months ago
I found debugging code with LLM most productive when I am in the loop. Don't get me wrong it can quite often find tricky bugs, those requiring some sort of reasoning (i.e connecting together multiple relevant pieces of information to arrive at the conclusion). However it often also suggests fixing issues that are almost always irrelevant in practice yet the fix complicates and bloats the code. LLM itself even accepts it when confronted. That is the main problem, in an attempt to overachieve at the task it is given, it can do deceptive or impractical things that can have negative effects. You might try to fix this with a config file but it just turns into a tug-of-war. So I find it more practical and trustable to simply eyeball the bugs it has found, implement (or ask LLM to implement) corrections to those and be amazed at how it found some of those bugs.
Ofcourse if you have asked LLM to write the software from scratch, you don't stand much chance of vetting the bugs via eyebaling. You have to spend much more time to understand how relevant they are. So your only option really is to defend the position of fully autonomous LLM coders...
abc 0 points 3 months ago
If you still have a working memory, you remember doing weirder shit than AI can ever dream of. Every one of us was a junior at some point. And judging by the comments here, most here still are.
ZILtoid1991 25 points 3 months ago
A guy, who made programming worse, especially in enterprise settings.
pivot_root 18 points 3 months ago
People don't like tracing what something is doing across seven 12-line functions spread through multiple files?
siftmama 12 points 3 months ago
Depends on which parts you look at. There is plenty that he wrote about that have made coding enjoyable, but yes, also plenty that is the opposite.
I never saw his book as a bible though. I always thought of it as a "here are possibly good ideas, see which you and your team likes".
jbrains 14 points 3 months ago
I don't know what those first two sentences are doing. This kind of thing is exactly what mesmerized young me and puts wise me off.
One thing worse than appealing to authority is appealing to your own authority.
IrateAnteater 7 points 3 months ago
Those two sentences just prove that the whole thing is made up. If he started coding in the 60s, he'd have to be over 80 now.
boatswain 5 points 3 months ago
Born in 1952: https://en.wikipedia.org/wiki/Robert_C._Martin
MirrorGiraffe 4 points 3 months ago
He could've been coding as hobby before it I suppose.
jbrains 2 points 3 months ago
Those sentences prove nothing of the sort. And you really have no reason to get that arithmetic so wrong. And you could have looked it up instead of guessing. He has a Wikipedia page.
He was born in 1952.
There are good reasons not to follow him. No need to invent bad ones. That only hurts the credibility of people decrying him in public.
thedeadwalking4242 10 points 3 months ago
I'll say it again for the people in the back, even if you are a vibe coding twat, well designed code is a MUST even more so.
If you want your LLM to preform even to the crappy level they can the codebase needs to be clean.
JakenVeina 10 points 3 months ago
I choose to believe this is satire. Also that this man holds no significant position of prominence within the industry.
/cope
ZombieCyborgFromOuterSpace 8 points 3 months ago
So... test driven agent developments?
SinAdjetivos 8 points 3 months ago
People don't want to hear it, but this should be more common practice especially for human written code, and it's best if someone specializes in doing this sort of QA testing specifically.
RicoRodriguez42 7 points 3 months ago
Dementia is no joke.
nanometer1625 7 points 3 months ago
I had a discussion with my boss today about potential ways to write code with AI and have confidence in the results without reviewing every line. You'd also have to automate the reviews in some way, and therefore also a way to confirm that the reviewer AIs are working properly, etc. The conversation discouraged me because it made me feel like I'll end up being a manager of AIs who write the code and test cases, and I'll just be an ape who manually tests some of the behavior before approving it for release. This is essentially what managers have been doing with human development and QA engineers in the past, but even so, I have a really hard time letting go and not reviewing every line of code myself.
ZILtoid1991 1 point 3 months ago
Every time I make 1 (one) mistake, I risk getting fired. AI does a lot more, yet gets to keep its position.
MonkderVierte 7 points 3 months ago
Actually great. Boss with the LLM-shares is satisfied, because he met the quota. Customers are satisfied, because the code at least works.
It might still not be efficient or maintainable, even have some in the tests unaccounted-for (because they're ridiculous) errors. But aside from that...
outerspace 6 points 3 months ago
It just means he is not doing anything important, in other words he doesnt have any specific thing in mind and it doesn't matter if it works exactly right or not.
It looks like it's working and for some people that's enough.
humanspiral 6 points 3 months ago
gherkin tests?
EnsignWashout 6 points 3 months ago
Human readable test code.
bitjunkie 5 points 3 months ago
path: 0 24935025 24935881, hotness: undefined, score: 5, children: 0
dismay3915 1 point 3 months ago
I've heard some stuff about bun and zig. Can you point me to what's the deal?
Jayjader 2 points 3 months ago
Not who you asked, but here's a link to one party's view (that starts by linking to something posted by another party): https://andrewkelley.me/...
dismay3915 1 point 3 months ago
Thank you
Snapz 5 points 3 months ago
"Look idiots, I have the machine that confidently lies ask itself if it did good. If the confident lie machine lies to itself and the machine being lied to lies again by saying to me that the first lying machine did not lie... Then I have 7 more lie machines do the same thing in sequence. So in the end, the only way I could fail is if all these amoral lying machines that lie, somehow ALL lied to each other, and then to me - which according to the lying machine, is impossible."
GoatSynagogue 1 point 3 months ago
No, he means that any code that gets through all of the tests works as expected and doesn’t break anything. That’s the whole point of unit tests and regression tests and all the others.
ZILtoid1991 10 points 3 months ago
I still writing my own code. I want to be able to debug it when it goes wrong, not rely on models becoming more capable at vibe coding.
WesternInfidels 4 points 3 months ago
Look, I don't care what you do with your gherkin, Uncle Bob, but you do it in private, OK?
gaiussabinus 3 points 3 months ago
This is such a sad case of age related cognitive decline
MirrorGiraffe 2 points 3 months ago
If it's his own products and no-one else needs to work that code I don't see a big problem with it, but the ways I've seen agents treat a code base just to pass tests is horrible.
BradleyUffner 4 points 3 months ago
Bob writes books about software development and has a huge following of mediocre developers that graduated in to management. Unfortunately what Bob says and does affects way more than just Bob.
MirrorGiraffe 1 point 3 months ago
I see, I happen to be a mediocre developer that graduated into management but I never heard of him before. Lucky me!
realitaetsverlust 2 points 3 months ago
Even if it passes every test, it can be shit code that is hard to read and extend
wyldrstallyns 1 point 3 months ago
Hey, you leave the legend, John Candy, outta this! 🥰
SaharaMaleikuhm 1 point 3 months ago
OK boomer
robert.meyer86 0 points 3 months ago path: 0 24931527, hotness: undefined, score: 0, children: 0
robert.meyer86 9 points 3 months ago path: 0 24931399 24931570, hotness: undefined, score: 9, children: 8
robert.meyer86 5 points 3 months ago path: 0 24931399 24931570 24932468 24933201, hotness: undefined, score: 5, children: 6
ZILtoid1991 6 points 3 months ago
Did daddy Elon or Dario praise you yet?
e8d79 5 points 3 months ago
In every single thread about people not liking AI you are there, being angry about people not liking AI. Whats the point? There are plenty of online communities for AI enjoyers like you. Try Hackernews they glaze AI all day long.
programmer_humor
@programming.dev
33653
2568
7610
Welcome to Programmer Humor!
This is a place where you can post jokes, memes, humor, etc. related to programming!
For sharing awful code theres also Programming Horror.
Rules
- Keep content in english
- No advertisements
- Posts must be related to programming or programmer topics
- If the mod doesn't find it funny, you're banned. Ha-ha!... For real: do not use the community for "statements". There are other places for such content. Keep it chill and funny.
go to feed...
programmer_humor
@programming.dev
33653
2568
7610
Welcome to Programmer Humor!
This is a place where you can post jokes, memes, humor, etc. related to programming!
For sharing awful code theres also Programming Horror.
Rules
- Keep content in english
- No advertisements
- Posts must be related to programming or programmer topics
- If the mod doesn't find it funny, you're banned. Ha-ha!... For real: do not use the community for "statements". There are other places for such content. Keep it chill and funny.
go to feed...
Inb4 the agents change the tests to pass the CI.
save