Why CoPilot Is Making Programmers Worse

Recorded live on twitch, GET IN
Article
darrenhorrocks.co.uk/why-copilot-making-programmers-worse-at-programming/
By: Darren Horrocks
My Stream
/ theprimeagen
Best Way To Support Me
Become a backend engineer. Its my favorite site
boot.dev/?prom...
This is also the best way to support me is to support yourself becoming a better backend engineer.
MY MAIN YT CHANNEL: Has well edited engineering videos
/ theprimeagen
Discord
/ discord
Have something for me to read or react to?: / theprimeagen
Kinesis Advantage 360: bit.ly/Prime-K...
Get production ready SQLite with Turso: turso.tech/dee...

[@pilotashish]

One thing that’s true for problem solving skills: don’t use it, you lose it.

[@headecas]

Most skills really

[@Varadiio]

I think AI is just another abstraction tier, though. This is as an aggregate over time, and for disciplined programmers, of course. To some, the internet is a place to copy code from. LLMs didn't suddenly change lazy programming in that way. As far as lost skills, well we don't retain much ability to write in binary. We have accepted that allowing compilers or interpreters to do the final and tedious step is an acceptable paradigm. We have also accepted Syntax highlighting as an important feature for any editor, despite it being a crutch of sorts. A more mature LLM may become an invaluable tool like all of those before, if the trade-off is deemed worthy. I think there are other factors in the software world that pollute the discussion. A programmer at a job counting lines of code as a performance metric will have a different incentive and intent with their LLM than someone using an LLM to help them learn programming in their spare time. Is it the LLM's fault that a company has an awful policy? I don't think current LLMs are worth very much loss in ability aside from perhaps boilerplate code that you could have macros for anyway. The future may be very different.

[@paillat]

That's why you will need Brilliant the sponsor of today's video

[@svenmify]

If AI makes you a worse programmer, you’re using it incorrectly. Use it to learn, and use it to automate tedious tasks. Be critical of what it suggests all the time. It’s simply not a good idea to rely on it too much

[@ItsBarmanji]

i mean how much it can hurt just copying some :nth Child and animation CSS from GPT directly...

[@masterwaylon]

Anyone else enthralled by the way ThePrimeTime highlights everything in a paragraph except the first and last characters?

[@Svetty00]

yes

[@yelr1136]

Oh my god I didn’t notice that until you said this

[@AS-wp3hb]

Off-by-one errors are hard

[@soulofangel1990]

I'm enthralled that you chose the word " enthralled " from all the words lol

Didn’t notice he did it. I do it because (in my phone) many sites select more than I want when I select the first and last chars. 😂

[@neruneri]

I've worked extensively as a translator between different languages. As in, not programming, normal languages. The whole part about erosion in your core skillset and even erosion in your language happens even with normal languages outside of a programming context. When I spent more than a year away from my home country, I started having trouble with just retaining my vocabulary in my native tongue. Took me a couple of weeks of being back home before I was back to normal. It's totally a thing.

[@padraigconnolly2991]

Genuine question, how are things going these days with translators and the whole AI hype, is it making many in roads into that line of work or is it very much hype driven like the programming world?

[@VivekYadav-ds8oz]

@@padraigconnolly2991 I imagine for formal and important meetings, people would definitely prefer a human translator. Could you imagine if the AI hallucinates something in a diplomatic discussion between two countries? Sht could cause a war 💀

[@neruneri]

​@@padraigconnolly2991 A mixture of both. It depends on exactly what type of translating work we were talking about. Machine Translations were already dominating certain parts of the industry, especially in terms of just translating for business sites and things that were "good to have, but not critical". The very cheap translation jobs for translating large amounts of text has been dominated by foreign people using MTL and then roughly editing the output since like 2010, and that section of the market has been absolutely further revolutionized by chat models because it functions similarly to what was already done but gives better outputs for the same amount of labour. From what I'm able to see, the scope of that type of work is certainly increasing as well. It's getting good enough that it is "acceptable" to more and more companies, not just the absolute cheapest ones. My take is that it is going to increasingly take over the low-quality and the mid-quality types of jobs more and more. "Bespoke" jobs are still going to exist though. There are a lot of types of job where high insight into context matters. Localization work for entertainment is an example of this. I don't foresee these jobs going away. AI tools might start being used here as well, but they will still need more human input to correct for context. Most AI and even the old MTL tools are very bad at context, especially cultural and cross-language contexts. Words can have literal translations but mean entirely different things in the other language due to context. This is where humans are unlikely to be replaced IMO. I've done a little bit of everything personally. I'm not going to be out of a job because of AI, but there are absolutely situations where AI can be used to help the workflow. AI tools aren't perfect to replace things like one-on-one translator work in person, but it can certainly be used in a pinch. I don't do that type of work anymore, but I don't expect those jobs to completely go away. It will depend on how critical it is to accurately communicate, if that makes sense. What I do most of the time nowadays is more along the lines of localization work. Not always creative projects, but my clients do pay me to be able to find the best way to get across the exact meaning that they were expressing in the original language. My type of work will not be replaced by AIs, but it could potentially be used in this process. For now though, I still find that it is roughly the same amount of work to just translate a document by hand from the get-go as it is to put it through a chat model and then correcting the result. An example of the kind of area I've done work in is translating medical documents and facillitating communication between doctor and patient. Both on behalf of the hospitals or institutions, but also sometimes on behalf of individual clients. The main thing I've seen being useful in that area has been that clients have had an easier time bridging some of that gap by themselves with the help of the AI, but it's not precise enough to always be used as a substitute for an actual person who speaks both languages. It's definitely been *helpful* however. Anyway, wall of text, but here's some of my thoughts in general without going into too many details .

[@neruneri]

​@@padraigconnolly2991 ​I posted a super long reply but it seems to have disappeared? Anyway yeah, there's definitely an entire part of the industry that has been dominated by machine translations since 2010, and they do very low quality but functional translations that are a little bit edited by humans and then just sent. This is incredibly cheap, and low quality, but it's already a huge part of the industry and that market share is definitely just going to increase over time. The theme though is that this is low consequence. While I don't do one on one translation work in person much anymore, I've done both that and translation of documents for hospitals. AI can and is used by patients in a pinch to try to communicate with their doctor, but nothing beats having a person there who can speak both languages. AI and MTL sucks at context too, so it'll never be good enough to use for localization work. I explained more in depth about that before my comment got eaten but I can't be bothered to retype it. Vivek is on the right track though. High precision, high consequence, or high context sensitive work is inherently a bad fit for automated processes, and that's *generally* what I work with, so I'm not exactly interfacing with the trend as much as other parts of my industry.

[@monkemode8128]

​​​@@padraigconnolly2991I used ChatGPT to learn Russian, and I'm able to have conversations with native speakers and I understand most words. I like ChatGPT more than other translators because it's able to explain things where a direct translation doesn't work or doesn't capture the meaning. For example misspelled/slang words, euphemisms, and sayings. Although somehow ChatGPT got it into its memory that I'm learning Russian and will occasionally respond to my English queries about programming in Russian. (I know I can delete "memories", but I find it comical and it's random, spaced repetition). It's been very accurate in my experience . That being said I wouldn't trust it to translate anything important, like another commenter said, you wouldn't want it to hallucinate during negotiations. IDK how it would do with larger blocks of text, I usually ask about individual sentences/words. It's good at rephrasing my translation in a more natural way as well, since the word order is arbitrary in a lot of... cases... I tend to default to a correct, but somtimes strange, word order/sentence structure which would be used in English.

[@swampdaddy4014]

I can't imagine what being self taught looks like in 2024 with all these things.

[@pixels_per_minute]

Same as it was before these tools came out. It's not like all the resources these LLMs leached off of no longer exist. Just avoid using these algorithms and find/learn what you need yourself without relying the robot. It also helps not using a search engine full of "AI" features.

[@steve_jabz]

Looks like when we invented high level programming languages and didn't need to use punchcards, vacuum tube arrays or assembly anymore. Whole lot of obsolete details were forgotten or not learned, but the information was still there for the once in a blue moon someone needed it.

[@hermes6910]

@@pixels_per_minute The issue if that youngster tend to use them.

[@iMagUdspEllr]

You can spend more time learning things than finding answers and writing it to test it for yourself.

[@hermes6910]

@@iMagUdspEllr Finding answers (which is in fact, solving problem) probably accounts for 50% or more of a developer's work. So it's essential to be able to find answers quickly and efficiently.

[@JamesPhipps]

Before I was a coder I was an artist & designer. My graphic design class year was the last with all analog coursework. We had to hand set type, make marks with rapidiograph pens to 1/128” precision, and layout pages for prepress with razors & tape. I had been using Photoshop, Quark Xpeess, Aldus Freehand, and 3DS Max on my own for ~5 years as had most designers & publishers so I wasn’t pleased. Control Z is my friend and wubbie. Fast forward 30 years and all the cool plugins & most of the desktop publishing tools have become Adobe rentalware, but I learned theory & techniques used to make things making learning new digital tools pretty straightforward. Explaining why skeuomorphic icons look like they do to folks under 45 is fun too.

[@idontneedname2529]

This is so true! I'm a 5th-semester computer science student, and I've noticed that whenever I use the IntelliJ IDE with the "machine learning" autocompletion, it shuts my brain off, and I just end up hitting tab to autocomplete. As a result, I have no clue what I'm doing. By disabling it, I activated my brain again and realized how much effort it actually takes to understand and write code.

[@JanVerny]

I mean, don't take it as a personal attack, but some of you guys probably just shouldn't be doing any mentally challenging work. If you had a junior sit next to you and make poor suggestions would you also accept them without thinking?

[@celdaemon]

First thing I did when installing the jetbrains family editors was disabling full line completion, just feels absolutely horrible.

[@clark4428]

@@JanVerny It may not be a 'personal' attack but it is still trying to be an insult. 1) There is a difference between the confidence of an AI tool that you *are* supposed to trust, supposedly, and trusting a 'poor suggestion' from another human where you will have to think it over. Hell, I'd say going with the human's suggestion over the AI's is better because you'd still actually have to write it out yourself and understand it. 2) You wrote this on someone's comment who made the active choice to critically engage with the medium to perform the mentally challenging work. Just feels like you wanted to sound superior and say it in the most needlessly snarky way you could.

[@Kwazzaaap]

@@JanVerny But if you can't trust it and have to review it, then it's no better than writing it yourself, completely defeating the purpose

[@JanVerny]

@@Kwazzaaap I was honestly kind od not planning to respond, because, yeah, I was probably needlesly snarky and arrogant in my original comment. But you guys have some big L takes. At least try to pretend to be decently competent. You get an insanely fast tireless junior and you can't be bothered to at least check his work? You turn off yout brain because you think you are supposed to trust the machine? What a sad lame bunch of pathetic excuses.

[@leakyabstraction]

It's not like a careful explanation is needed here... the effect is completely obvious. It's also obvious why would it be lucrative for Microsoft to make programmers sorely dependent on their service.

[@almazu2770]

When I learned Chinese I wrote every character by hand and remembered how to write every character I know. Then I started only typing the characters using pinyin(basically pronunciation) and suddenly I realised that I couldnt recall how to write a certain character and I had to look it up on my phone or somewhere else. Copilot seems to work in a similar way

[@Chisegh]

Same for me with Japanese. This is also true for Japanese people. Since we 99% write using computers or smartphones these days, it is not uncommon for people to have to look up how characters because they forgot how to write them.

[@zeppelinmexicano]

Good analogy. And as you now there are LOTS of gotchas that will find us in human languages if we don't commit fully and stay committed to all the skills needed to say "I speak that language". We're just talking about learning and staying committed to it, which is easy to let slide too long.

[@quinndirks5653]

I guess there is a similar thing in english where you can forget how to spell certain words, and your vocabulary can diminish over time if you don't do a fair amount of reading and writing.

[@Strammeiche]

learned helplessness is really important. a junior I helped had the problem to just want to solve and rush from problem to problem - never really understanding what or why worked. It is helpful in the short term or when you must solve a problem fast but can hinder your progress extremely overall.

[@2n3g5c9]

LLMs make pretty good rubber ducks. Surprised it wasn’t discussed at all.

[@wolfgangrohringer820]

Agree! This is my main use for them. Which is why I actually prefer the chat interface to something like CoPilot. But then I am slowly getting old, and perhaps change-averse.

[@hookflash699]

Breaking: When People Stop Exercising, They Lose Fitness!!

[@rumplstiltztinkerstein]

I use AI for explaining what an existing function does. Since it is trained on the docs, it will most likely just simplify 10 minutes worth of documentation into a single response. Asking it "What does this part of the code do" is much more reliable than "please implement a function that does Y". The former it will just explain the quick definition of the docs, while the latter almost always will generate buggy code.

[@FeLiNe418]

Why not to rely on a robot for everything? Well... you need to convince your bosses why they shouldn't replace you with a robot

[@rns10]

I have this weird flex to have never used it, because someone else writing code from what i say, always comes wrong. I rather take things in my own hand and write good/bad code and its on me to fix it. A colleague is different because we both can share knowledge (the context of the project is better). So we can give each other feedback as well.

[@mini_bomba]

On that LSP and the stdlib topic: I often use LSPs, but never use them for learning the standard library. I also never know the entire stdlib, but I am often somewhat familiar with the areas I've previously used. I very often have the stdlib (or third party library) docs open on my second monitor. I don't use LSPs for discovery, I use LSPs to make typing out the code that I've already planned out in my mind faster, and to avoid making an accidental typo while doing so. What I actually use to aid in discovery is a linter. When I program in rust, I turn on the pedantic clippy lints. It then sometimes catches when I write dumb code or reimplement the standard library and tells me about this stdlib function that I may not have known about before. It's always fun seeing these lints.

[@justinfricke9182]

One thing that I think often gets overlooked is that programming isn't this static thing. 20 years ago TS, Kotlin, Go, Rust, etc didn't even exist. Even old languages like C and C++ get updated with new features. How are LLMs going to be trained to use new features and new languages without programmers producing code? And how good will that training be if the quality of the code LLMs are trained on is poor?

[@-_James_-]

LLMs are trained on open source. You don't get much poorer in terms of quality.

[@killsode4760]

More like they're trained on any code off the internet. Not matter if it's some brand new green coder or someone developing a well made tool.

[@quezabitheone4457]

On top of that, the amount of times projects are completely halted because of lack of fundamental knowledge.

[@OfficialBeeswax]

Whenever I need to figure out the solution to a complex problem, I just like to take the dog for a walk (I live in the countryside, so plenty of room here) and after a bit the problem and its solution will just come to me. Absolutely no interest in handing that off to an LLM.

[@uiuxaidesign]

yet, here you are, day after day, talking, commenting about AI. I predict you will leave a few dozen more comments in the future about AI... regardless of the comments will say. My point is, you're being hard headed. You should be more open minded and appreciate AI more. Just because YOU have no interest in LLMs and solving problems using AI, doesn't mean progress in AI field will stop! I'm sure you keep up with AI news every other day now!

[@pilotashish]

The best balance I’ve found for AI based in-editor autocomplete, is to have a hotkey for on demand completion. This allows you to focus on important logic, and use the ai for boilerplate code like mock data.

[@triducal]

the only thing i ever use copilot for now is just mock data and writing tests

[@goldsucc6068]

You are writing low quality tests then. Data must be extracted from working system when possible, faking data is last resort

[@themartdog]

I'm still problem solving when I use copilot, the problems are just higher level. I really don't see what I'm losing by copilot writing the 5 boilerplate crud functions rather than me spending 30-60 minutes writing them.

[@siya.abc123]

I've never used any of these copilots because I heard Prime saying he doesn't want to become a read-only developer because of these tools. That was a profound and defining moment for me

[@derp2397]

people used to debug with literally reading the code long time ago, you know

[@filipg4]

As someone who had a lot of trouble integrating new programmers into the team specifically because of their dependence on LLM-s, please for the love of god know when to stop and learn something on your own. It feels like the new generation of programmers are just LLM proxies, how will such a generation keep the lights on when older programmers move on?

[@williamdrum9899]

Kind of like how those older programmers are "compiler proxies"

[@TheMidnightillusion]

Maybe if the vast majority of tech documentation wasn't an incomprehensible mess to newcomers, they wouldn't have to rely on LLMs to explain it to them in ways that actually make sense....

[@JohnnyThund3r]

@@TheMidnightillusion I mean, at that point, you're generally suppose to just read the source code.

[@iMagUdspEllr]

How is reading and understanding the code written by a jerk on stack overflow different than reading and understanding the code outputting by an AI? If you mindlessly copy and paste either one, it's bad. But AI is just a faster, more polite teacher that gets things wrong (just like humans do). If they don't understand the code, they tricked you during the hiring process so that they understood how to code, and that's partially your fault. Learning from a forum, another person, documentation, or AI is the same.

[@iMagUdspEllr]

​@TheMidnightillusion Right. As soon as the old heads get an English degree or a teaching degree I'll crawl through the drivel they wrote. Not everyone is a communicator. Don't worry, AI will do that job your for you and I don't have to listen to your snide remarks while I learn.

[@XDarkGreyX]

My coworker keeps in memory countless details about past projects, often even those he hadn't even been involved with directly. Meanwhile my brain tosses the info out the window after sometimes even 3 months. Add that to the 'skill' of which I also forget a good portion constantly.

[@Algorerhythm]

That mentality switch you are describing around 9:15 is what you get out of the box from practicing pair programming. One brain codes while the other reviews it.

[@marty0678]

I don't understand many of these arguments like that presented in the article because nothing stops someone from researching what the LLM generates. Whenever something is suggested I don't immediately recognize or understand, I go look it up in the docs or step through with the debugger and make sure I know what it's doing and make tweaks if there is a better way than what was generated. The 'problem' these articles present is the same 'problem' that has already existed for years that you get from SO pasters. If the developer doesn't care enough to understand their code, they already had that issue before an LLM gave them an answer. LLMs just get them to the same issue faster.

[@Salantor]

Yes, and that is a problem, not "problem". We already had enough people just copying and pasting code without any deeper understanding. Now we have more of said people using tools advertised as being on a PHD level, if not better. And we are not teaching people to be suspicious enough when it comes to results.

[@prosperomiponle7645]

This actually should be top comment. It’s definitely the fault of the person, not the tool. But one could argue that the availability of these tools makes it easier for people to be complacent about actually putting in effort.

[@segganew]

This is my additude. I have never trusted LLM code, and if I don't immediately understand the code it generates, I write it myself.

[@fabianletsch1354]

As a senior developer i strongly disagree with this. Coding is like a sport. Anybody can understand it. Just like i know the basics of baseball or soccer and i can even do many things. But the hard part is having things in muscle memory, having a feel for something or the right intuition and that does not come from looking up things, but actually running into the issues and dealing with them instead of getting the correct answer and then looking up why it is correct. Or think about maths in school. Do you retain how something works when being shown the answer and then shown the way they got there or do you understand things by actually going through the problem a figuring out the solution. Or think about knowing something. We all know about obama, we have seen him on tv, we have heared about his politics. But do we actually know him? Like do you know how his evening looks like or will he call you by name if he sees you? No because knowing somehow is more than that. I dont really know how to put into words what i mean. But i guess you get the gist of it by looking at those examples. Going through a problem or getting handed the solution and then looking up why it is the solution are just different things.

[@bonerjams2k3]

Human beings are LAZY and always looking for a shortcut. You might look things up when you see something you don't recognize, but most people will not as long as it works. Stack overflow continues to exist in large part bc of that.

[@nasko235679]

As a learning developer I thought I was slick using ai to write my db queries, and parts of my react code but then I kept finding myself stopping coding whenever my free GPT/Cloude limits ran out. That's when I knew I was in trouble. Been AI free for a week, and I plan on using it in extremely limited cases exactly because I've become a code reviewer (which I don't even have the skills to do concidering my experience level) instead of a programmer.

[@anotherdamnuser]

The biggest trend in programming for the last 10 years was "Become a dev in 3 months", well, some people believed it, now they call themselves programmers, not copilot fault, this "downfall" has been happening for a long time before LLMs.

[@k98killer]

Eventually, we'll need the assistance of an AI to figure out the prompt for our AI assistants.

[@thunder852za]

I agree with your last point - it remains to be seen if relying on the robot is a good or bad idea. I liken it to a calculator, before the calculator it was all slide rules and understanding adding and subtracting. Clearly, in this example calculators were good and positive, turns out it allowed people to solve more complex problems but still know roughly how to to basic arithmetic. Perhaps one need to learn the theory behind a tool in uni and get tested on it 'closed' book style, then after you can use it with 'gay abandon'.

[@krux02]

Code is a liability, not an asset. AI is Autogenerating liabilities, it doesn't fix anything.

[@steve_jabz]

Skill issue. Doesn't happen when I use AI.

[@SimGunther]

​@@steve_jabzCare to share that AI?

[@ambralemon]

​@@steve_jabzyour comment history on the channel is so funny, lmao

[@steve_jabz]

@@ambralemon yeah

[@theairaccumulator7144]

@@ambralemon he might be AI himself lol judging by his comments

[@nightshade427]

When I hear people say "why not rely on the robot" I get sad because I don't think they see the implications of what they are saying. If we rely on the robots then the skill will die, this leaves only a handful of llms that code everything. This means we have lost the means of production for software, and one softwares greatest strengths is that the means of production is in the hands of the people. The reason they give it in school for free and ceos are saying stop learning to code is because they want to control the means of production. They don't want anything made that they don't get a cut of or that they can control. Apps in app stores, centralized cloud infrastructure, and now code itself.

[@hellelo.5840]

We forget because we try to find a common pattern in multiple languages and remember only the common parts because we think it's enough to restart with.

[@themalmana]

EVERYTHING that makes a cognitive problem easier will decrease that skill

[@vitalyl1327]

Huh? The very nature of problem solving is in finding ways to make it easier.

[@themalmana]

@@vitalyl1327 And every problem that has been made easy in past is no longer a skill that we maintain.

[@anishbhanushali]

There is a place where LLMs for code fits perfectly. It's docs !! I don't like to go through docs of pandas for a small numpy like function , if LLM does this for me(which it does), it's a win win!!

[@sealsharp]

There are parts of programming where the robot can do it, because others have done it enough to teach the robot. There are parts of programming where the robot can not do it. And instead of asking "should i use the robot to do what the robot can do?", would it not be better to do things that the robot can not do? Because you will not get paid for what the robot does.

[@johnpekkala6941]

The most worrying part is the risk of AI turning programmers into "script kiddies" = just copy pasting ready made code with no understanding whatsoever how it actually works or what it does like "just paste it in there and it will work somehow". But why and how does it actually work? That understanding and skillset risk to go lost. I read in some other forum that the technology in Star Wars is not evolving at all over the course of the series because noone there any longer understands anything about the actual technology and therefore can only copy what already exist again and again = technological development stagnates forever. AI is after all not really intelligent and can not by itself create any new things like we can but can only reuse what humans once have created. A sort of analogy is that AI is like a blender that u toss fruits and other things into in different proportions, blend together and then u drink the finished smoothe or whatever but a blender can NOT create new base ingredients like new fruits, berries and such but can only blend together what already exists. Same goes for AI. It only reuses and blends what we have already created, like AI can for example not do things like improove or invent new programming languages, art forms ect by itself but just take and reuse whats already there. It only seems intelligent because we have fed it the entire internet worth of content but it can never learn to "think", work and create like an actual human mind. Its still just a machine.

[@mrgamer-lu1im]

Yeah man this is so true because I asked an ai to generate a code to solve a problem for me and If I wasn't a good software engineer I wouldn't have realize it gave me a garbage piece of code

[@rubend824]

i tried copilot for a couple of weeks and i'm quite sure it took me just as much time to fix its code than it would have taken me to do it myself from scratch. I also found it very invasive. I gave up and went back to chatgpt for basic stuff, like parsing jsons to classes and that sort of stuff, and maybe ask for available libraries, but never to code for me.

[@huuhhhhhhh]

If we're going to have "robots" design, build and run our applications 100% autonomously, then what's the point programming languages at all? And, btw, when's the last time you when to a concert performed by a clockwork piano?

[@Delaterius]

Historically, automation doesn't make artisans worse at their jobs. It makes a class of laborers who are not artisans, but who can use automated process to make something that is functionally equivalent to what artisans make. The mechanized loom didn't make weavers worse at weaving. It made the time of poor people a commodity for the rich. The people who stayed weavers didn't get worse at weaving, and their work didn't get less valuable. If coding AI follows the same pattern, your goal should be to stay an artisan because if you become a worker in a code factory, your labor is going to get a lot less valuable

[@riptorforever2]

The following would be a healthy way to use copilot? 1) Use it to generate code that meets the design of a function that uses a library that you are not familiar with. 2) Debug the code to understand each transformation performed and the existing methods of each instantiated class. 3) Create your own function based on what you learned from the generated code.

[@lelsewherelelsewhere9435]

Eroding of programming skills isnt AI/copilot's side effect, it's the goal!!!

[@bryankorg6385]

Refactoring is a great point. It is way more unlikely (due to laziness) that you will refactor code that seems to work and that you did not write yourself.

[@ifonlyicouldenglish]

I ended up creating my own self-hosted copilot using Ollama, but I found that using AI for coding tasks is kind of annoying as a more experienced engineer. It's almost never able to predict what I'm writing until I'm practically done writing it. It saves me a few keystrokes here and there, but it's otherwise not all that great at writing useful code. That said: It's become more useful over time as it samples my code and comes to understand more about my style, but it's definitely a work in progress... 😅

[@SidTheITGuy]

I feel like this blog was copied from my video on the topic of not using AI for coding. Just a hunch lol.

[@artistry7919]

I feel like this is a really common opinion. I'd never seen someone say it on yt and already had the same opinion

[@kickhuggy]

I can’t believe how strongly I disagree with this take. One, all the issues brought up with AI (bugs, maintainability, etc) are currently already a problem in spades… you can counter act it with tests (performance, unit, functional). Two you’re trying to prematurely optimize by learning skills that may or may not be useful in the future. It’s one thing to believe remembering syntax is important (maybe), but it’s different to say this tool might not be available in the future, so I’m going keep using hammer and nail. Three, most tech companies reward output, not process. If you get your work done, no one cares how it’s getting done, as long as you’re not breaking laws. If in the future there’s a problem, you solve it with the tech available at the time

[@zeppelinmexicano]

At least make a good effort to learn and remember once an LLM finds a solution you could not find. To just plug and run, that is a problem of attitude about learning. You cannot get better that way.

[@thingsiplay]

Ai is for people who don't want to program.

[@TimothyWhiteheadzm]

This is the age old argument that is used by old people about children who use modern technology. 'Not learning to multiply with slide rules or log tables will make the children lazy and dumb'. If a tool allows you to do your job faster then it is a good tool and if it allows you to do your job without certain skills then those skills are no-longer necessary skills for the job. I am talking as a programmer with over 30 years experience beginning in C and assembly language. Embrace new tools and learn how to use them effectively.

[@guitoo1918]

Because of the free licence for students, the new devs that are going to hit the market in 2 to 3 years will be a totally different breed.

[@hookflash699]

Oddly, this actually kinda gives me hope, in a way. I can see how, a few years from now, devs who avoided AI coding tools will be in high demand because they'll be the only ones who actually maintained their skills.

[@PP-ss3zf]

good for experienced devs, bad for new devs. nexttttttt

[@DarkorbitForever12]

Not wrong!

[@MooThedevO]

The best advice here: Fix the blind spot. Do not become helpless.

[@xtieburn]

What helps me is that I dont have the AI produce some code and Im done, I look at the code, either understand everything as an implementation I would have done more or less the same and use it, or immediately start wondering: Why is that like that? Is that better than such and such? Whats the reasoning behind this part? Sometimes its logical and you can work it out, sometimes you need to really drill down in to it. (and of course sometimes its just bad code for your context, or more rarely, bad code full stop.) When its working well it feels really good, because the AI is just so fast at expanding on things. I work for a small company, have by far the most experience, but am not exactly the best dev out there, and this is like having a forum you can rapidly bounce things off who will never get tired or frustrated or tell you to just RTFM. (Oh, but I dont use in editing AI. Anything that can waylay your process of digging in to whats being generated is dangerous, especially when it can worsen your ability to write code fluently.)

[@GrahamAnderson-z7x]

Working with AI (at least in Cursor) makes me a better programmer, because Sonnet often produces code riddled with errors, which I have to research and fix. Oh wait? Why am I using AI again? Training the model for the next generation of prompt engineers I guess...Sorry for rant.

[@MissMyMusicAddiction]

llm's also make it much easier to do things the hard way. the argument that llm's make your skill worse is like arguing that driving gets worse if the car does the driving. landings get worse if the planes autoland. cooking popcorn gets worse if you throw it in the microwave. what?

[@everythingcouldbesimplify818]

I was writing my own thing very performatic and then copilot kinda of generated a lot of improvements to it, and I just end up using copilot version, so it's like I did nothing at the end of the day, it's like it needs your code as foundation so it will start making correct guessing for what you need next.

[@cyko5950]

The thing about copilot is that it tries to write code for you. What i actually want AI for is to explain concepts that i do not understand. I can do the implementation by myself once i have grasped the concepts.

[@krumbergify]

I don’t like the disconnection between reading the code a person wrote and then discussing the code and the problem with the person. I insist that the in person interaction should provide more value and deeper understanding than me looking at the final work.

[@lelsewherelelsewhere9435]

For students, it depends... It helps me learn new things and ways of doing things, which I look into and learn. It seriously LOWERS THE BARRIER TO ENTRY for many concepts. If you're lazy and dont look into the solution, then yes, it's worse. For good students, it makes them better. For bad students, it keeps them bad/prevents school from forcing them to learn.

[@Teodor-ValentinMaxim]

I see tools like Copilot as the next abstraction of previous generations. Before NodeJS, you needed to know how an http server works, now you have people who can't build a simple http server without using a framework like express.js.

[@draken5379]

I review myself on every push to a repo. Time consuming, but often ive caught random bugs this way.

[@Oler-yx7xj]

I wonder whether this "learned helplessness" thing Prime is talking about comes from a lot of programmers coming from an exact science background. In school math, the problems are exact and you are expected to give perfect, exact answers, and if you don't understand the problem, the teacher will always clarify it. Programming just isn't like that. I see this "things should be precise and of they aren't, I won't do anything" a lot in my fellow classmates at university, so it looks like the mindset is learned quite early

[@krumbergify]

Sure, I can look up individual facts in almost all fields, BUT I can’t draw meaningful conclusions if I don’t keep a wide range of facts in my brain at the same time.

[@MrWorshipMe]

I write my code and then let the AI review it for me before I let my co-workers review it. I have to say that these AIs are waaaay too nice.

[@Karurosagu]

Knowing what you're doing is important You can't know everything that's going on at a 100%, that's most likely not possible, but you also can't rely 100% on the robot to do everything and remain ignorant

[@mduvigneaud]

Imagine studying to become a professional chef and all you learn is how to cook Hamburger Helper and reheat packaged microwave meals.

[@rainbolt5173]

Core programming skills are the skills that survive language hops. Language specific details are the opposite of core.

[@biggerdoofus]

To be fair, a lot of Lua tutorials don't seem to know how for loops work either. :)

[@themartdog]

I guess it's what metric matters most to you. The speed of getting multiple projects done in like 1/3 of the time is more important to me than worrying about atrophy of how to build a CRUD app or whatever 🤷

[@mypaxa003]

Maybe I'm using Copilot wrong, but I'm not generating a lot. Yes sometimes I ask to generate some algorithm that I never learned before, but I never use it right away, I'm disassembling it in bits, trying to figure it out, and applying it after that. I'm only accepting the small bits I wanted to write. I know that I don't like to type in all those tiny bits manually anymore, but it is not hard to gain this ability back. I've tried to disable copilot for 2 days and yes I had some issues at the beginning, but it became fine at the end of second day. So I don't feel bad about using Copilot. But I would not recommend it for beginners.

[@williamdrum9899]

C: First time? Assembly: First time?

[@UCjNrKLyRJI-abFA8qiNo92Q]

no one is a 10x developer if everyone is a 10x developer

[@handlechar568]

possibly hot take: if you're not re-checking/reviewing your changes as a whole against dev branch or whatever when you submit a PR, you are probably an awful programmer and everyone hates you and your awful code.

[@redwrathable]

Similar to the constant debate of using calculators in Math class. IMO, both extremes have equally good points, and it should be a balance.

[@Nstromzz]

Using Ai to learn can be great, just dont copy paste it, it will lead you to not even understand the "magic" some IDEs bring. But if you keep asking for otherways the code can be written or if it can be made simpler or maybe ask it for explanations or even a problem using this that you yourself can solve. or when it churns out something you recognise, search it through the docs to read more about it before implementing it, and dont just read the explanation GPT gives.

[@vladimirkraus1438]

The problem is more general: In the future people will delegate all activity which require thinking to AI, starting already at very very young age. As result, the next generations will be totally stupid... Idiocracy will become reality. That is for sure. It will only happen with a different mechanism than was shown in that movie.

[@marc_frank]

people don't know how to use an abacus anymore, some don't even know what that is. people didn't care about the use of the abacus itself, they only want the result. it was the most advanced tool available to make the process as easy as possible. then there were calculators, which is even easier to use, so everybody switched tools. programming languages are a tool to accomplish some result. if there is a new tool to accomplish the same result, tools will be switched and the one before will be forgotten eventually. the most successful inventions are ones that allow a large number of people to be lazier than before. just like the dishwasher didn't create more leisure time, just hangin around, time that is saved will be filled with more meaningful tasks. wich might be able to be automated in the future, too.

[@alphoz123]

I don't know how assembly works, and with async/await I don't care how the generated code actually look like. From assembly perspective the code I have written in Python is probably far away from optimal and it doesn't really matter. So I guess this AI thing will eventually evolve into something at another level.

[@YaserFarid]

I do not enjoy reviewing code of others, but I love to keep optimizing my code.

[@kyleMcBurnett]

I catch way too many bugs in self review. I love and hate it.

[@JohnnyThund3r]

There is no disadvantage to using A.I. to read code for you, absolutely none in my view. There is a disadvantage to relaying on A.I. generated code you don't understand. Simple solution is to not use the code until you have the A.I. explain the code to you, and refuse to implement it until you understand it. In fact in most cases this should be standard practice unless you really just gotta move quickly.

[@benbuzz790]

“Old man yells at cloud” People said the same thing about texting in the 00’s - all the slang and shorthand would make students worse at writing. Turns out, the opposite happened, because students were writing *more*. I would argue the same is true here - these tools can introduce new programmers to more ideas more quickly than they would otherwise. Ancient humans complained books would ruin people’s memories. This is just the 10,000th example of that logic being misguided.

[@noob3lite]

Are you an developer? I write Software for 30 years now and most of the generated code is crap. If you use the tools as a google in your ide there are fine. Or help you refactor sth if you changed some function signatures its also fine. But relay on it only it makes you a bad coder

[@maidenlesstarnished8816]

I agree 100% that it can introduce you to new ideas quicker, but at least for me, everything prime is saying is right too. So it's a bit of a double edged sword.

[@voiduzumaki2603]

For me it feels almost like the opposite - as beginner, I often let AI do the writing in the beginning, because I have no clue about a language, but since I have a usecase, use AI. But once I work further on it, using AI either takes as long as writing it myself, because it needs multiple attempts or I need to describe it and have it written in the same speed. It's just great to see a function used in a specific way, or have a general idea of how something could be done - which then allows me to build on it. Make mistakes, find out what's wrong, and therefore improve. The same goes for using a new environment or library. It just makes finding the basics quite easy. In conclusion, I think AI is a great way to start, because you don't start from completely nothing, but even while still working on the basics, one should transition to writing oneself, because AI just isn't the solution to it all.

[@DerH0ns]

LLMs are awsome at genrerating documentation though

[@realkyunu]

If you have healthy legs and you use a wheelchair to get from a to b all the time, you will lose your ability to walk.

[@judewestburner]

They said the same thing about Google. You can now just look up the answers.

[@eugeneponomarov7429]

*"If you as a developer do not understand the code..."* - yeah, probably you don't need to understand the whole code in your application, but you definitely need to understand the code written by you! If you are creating a PR and cannot explain the code you want to merge, then how are you still employed???

[@Titere05]

Something in life that doesn't take effort to do or build? Surely that's possible

[@lukaszmatuszewski]

I'm not going to overmedicalize, but I think switching between vim and GitHub UI for particular tasks makes perfect sense especially in ADHD and similar conditions. We are environment sensitive (some might attribute it to brain working in default mode network), so why not use it for our advantage?

[@jjmalm]

Did ... Did stackoverflow write this post?

[@soulGrafitti]

The last paragraph of the article is poorly written. The first sentence is not even complete - it's an IF statement with no THEN. Oh, THEN is in the following sentence. It's as though the first part of the article was written with some consideration and thought and the conclusion slapped on in a rush. Ironic - author's English writing skills have clearly atrophied. Too much reliance on auto spellcheck and grammar hints? Unfortunately the poor grammar and editing tends to pull you out of focus on the content. It's the literary equivalent of sputtering instead of speaking though in this case goes along with the old-man-shaking-fist-at-sky sort of summation. "If you only rely on things to give you the answers all the time it will make you worse. The ability to do that yourself is the skill you're after and programming is the expression of of that skill." Great statement of why I was drawn to coding in the first place. I know I understand something when I can represent it in code. Well, many things - emotions do not code well, but that's a different channel. Writing code is modeling something so I can play with, or manipulate, it. I think a lot of discussions about code conflate this sort of macro, strategic view with the micro, tactical view that is, by its nature, very different. For example, I think the side discussion about reviewing code vs. writing code and the effect of setting, going to a coffee shop to drill down on a specific task, is touching on exactly this point. For me it goes back to learning in school that the action of figuring out the answer to a test question and the action of bubbling in the correct circle involve different parts of my brain. The optimal approach is to avoid conflating them by working out the answers in one pass and recording the answers in another. So figuring out the purpose and design of something and the specifics of how to make that work are often different mental tasks. They overlap but aren't exactly the same.

[@defipunk]

Well, either AI is too stupid to program or you lose your analysis ability. You can't believe both, unless you think basic syntax is programming. He even makes that point by contradicting himself right after... "Programmers can quickly create working code"

[@babstra55]

I wonder though, and this might be completely different type of motoric skill... but in chess you can take even years off and when you come back you're exactly where you left from. like yeah first day you're worse and you feel like you forgot all theory, but in like a week you're right at the same rating you used to be. I took 8 years break and came back at the same ~2000 rating I left from, and I've seen people do the same after 20 year break. so I'm wondering if the coding aptitude would come back in a 1-2 week ramp up just as well, it's just not instantaneous and it does require SOME work.

[@YouReyKarr]

Look, LLM's can't code all that anti-AI rhetoric, etc, etc. But at the end of the day, who remembers their maths professor saying "You won't have a calculator in your pocket, in real life". They were wrong.

[@stitchfinger7678]

But ai literally isn't a tool like a calculator You're literally having it do every letter of work for you without having to do anything And besides, once you left like 5th grade, a calculator couldn't solve the whole problem for you anyway; as soon as algebra hits the scene you have to do work on paper anyway.

[@Userr18362]

@@stitchfinger7678for a handheld calculator sure, but a computer calculator like symbolab can solve pretty much every algebra and calc problem

[@alcar32sharif]

Use LLMs to learn to ask great, mindful and structured questions (aka prompts). Not for coding.

[@Daniel_Zhu_a6f]

why is it bad to rely on a robot? because our society is structured in such way that it will be inevitably used against you. medieval craftsmen (luddites) could figure it out (and they were 100% right, the automation was used against them), why can't a modern programmer?

[@thunder852za]

Agree - if you have been coding for 5+ years or something then I think AI is probably quite good for efficiency. For new comers I think you end up not getting that deep knowledge. Depending on what I am doing - I like to write the code, ask the AI to write the tests and docs (the mundane shit). Then I review the tests to check its testing what I want and the edge cases etc. Also when solo deving AI is very helpful to be a sound board idea off, weird as it sounds.

[@olbluelips]

I’ve been meaning to read this article for like a week thanks for doing it for me prime

[@lennysmileyface]

Turned off using public code and have it as autocomplete for basic tedium.