fuck you bill (lemy.lol)
πŸ‘€ 1
 

top 65 comments

sorted by: hot top controversial new old
[–] 24 points 6 months ago (2 children)

Bill doesn't understand liability clauses in contracts when he sells his vibe coded shit as a SaaS platform and gets popped because AI forgot about SQL injection.

  • source
  • hideshow 2 child comments
  • [–] 22 points 6 months ago (2 children)

    β€œDid you just have Claude ship all this code?”

    β€œYep”

    β€œYou shouldn’t ship code you don’t understand…”

    β€œGood point. Claude, go understand this code for me!”

  • source
  • hideshow 2 child comments
  • [–] 1 point 6 months ago

    Got pulled into a meeting where a web dev contractor we hired stated, β€œI can’t promise these changes, it depends on how we can get CoPilot to do them”. I don’t think my bosses care because they want their bosses to know that they are, β€œworking with AI”.

  • source
  • parent
  • [+] 35 points 6 months ago* (last edited 6 months ago) (4 children)
  • [–] 6 points 6 months ago (1 child)

    Sorry, you were hired as a prompt engineer, your prompt wasn't good enough to make perfect code, so you are fired

  • source
  • parent
  • hideshow 1 child comment
  • [–] 50 points 6 months ago (15 children)

    I've seen the comments AI adds and yeah... No.... It's often pointing out the obvious or even in some cases just misleading.

  • source
  • hideshow 15 child comments
  • [–] 1 point 6 months ago

    Agreed it's why if I'm asking for llm assistance I will generally start with a design for a component and ask it to follow that and comment accordingly usually leads to much better results than blanket asking it to do something for you

  • source
  • parent
  • [–] 0 points 6 months ago (5 children)

    You can add instructions to not comment, you can also have it explain what it does at every step, not everyone just doesn't care about learning. It can be a very effective teaching tool if you use it that way. 🀷

  • source
  • parent
  • hideshow 5 child comments
  • [–] 4 points 6 months ago (2 children)

    AI is a terrible way to learn something. It will do something wrong, explain it incorrectly, and you will have no idea.

    AI is only useful if you are able to spot and correct the mistakes it makes. Because it will make mistakes.

    Very effective teaching tools already exist if you want to learn.

  • source
  • parent
  • hideshow 2 child comments
  • [–] 0 points 6 months ago

    Out of the box yes this is true, but:

    1. Custom instructions go a long way
    2. Review the code yourself, tell it what to fix, and it will fix it. For me it often takes like 5 rounds of this before the code is fully polished to the point I'm proud of it. And you know what? It's still MULTIPLE times faster than typing code by hand. And at least for me, the quality is higher, because I have 12 different agents that review the work too and they catch additional issues that even I missed.

    If you or others ship shitty code don't blame the LLM, the issue is entirely the engineer using it wrong

  • source
  • parent
  • [–] -1 points 6 months ago (2 children)

    So... indistinguishable from the statistical mean of human generated comments.

  • source
  • parent
  • hideshow 2 child comments
  • [–] 17 points 6 months ago (3 children)

    A lot of big companies are basically forcing you to be Bill. They try to track AI usage, and make sure everyone is using it. Because they invested so much in AI, they need to force it, to make it a self fulfilling prophecy. It’s truly one of the dumbest things to behold.

  • source
  • hideshow 3 child comments
  • [–] 5 points 6 months ago

    Nightmarish. Can you make the AI write up new documentation every time you want to push a change, so it looks like you're using it frequently but you still get to write the code yourself?

    I would love letting LLM deal with documentation. It's the bane of my existence.

  • source
  • parent
  • [–] 5 points 6 months ago (1 child)

    Does Bill have the flaming frenzy within?

  • source
  • hideshow 1 child comment
  • [–] 9 points 6 months ago (8 children)

    I know I'm gonna get flamed for this, but here goes.

    I have vibe coded a system at work that has enabled me to deliver value in a fraction of the time I expected. My verification steps have been around whether it does the things I told it I wanted it to do. I'm not maintaining the syntax and I'm not expecting anyone else to. Ever.

    That said, our teams that deliver products that touch customer data or financial records....they shouldnt (and dont) engineer this way. The tech isnt there (yet).

    Let the flaming commence.

  • source
  • hideshow 8 child comments
  • [–] 8 points 6 months ago (4 children)

    You make the billionaires proud, such a good lil capitalist

  • source
  • parent
  • hideshow 4 child comments
  • [–] 1 point 6 months ago (2 children)

    "...enabled me to deliver value in a fraction of the time I expected."

    I don't wanna flame you for it.

    This is kinda where I see vibe coding taking off the most: The same phenomenon as using LLMs to summarize and reply to pithy business emails.

    Business gets so unbearably businessy, people are using machines to bypass the inherently un-human "professionalism performance" for them.

    It might not be work anybody can claim to be proud of, but right now success for the professional-managerial class runs on looking busy and circling back to synergizing the workflow with best practices for optimal returns regarding key performance metrics 🀒 or whatnot.

    I don't blame people for it, in a work context. Looking impressive with AI tools is now a survival tactic when working under normies holding the purse strings and investing stupid amounts of money into the bubble. They've forced people to be part of a circular, self-reinforcing imaginary reality they're profiting from.

    So, I don't wanna flame you. I just hope you're doing something fundamentally human to keep your soul alive on the side, at least. Something you as a unique human being on this earth can be proud of. <3

  • source
  • parent
  • hideshow 2 child comments
  • [–] 1 point 6 months ago (1 child)

    Honestly im proud of the problems I'm able to solve today now that I can use AI to do it so quickly.

    Even when I stop and manually check all the work the AI has done, it's still much faster and I'm having to rely on my knowledge and experience to do so. When I'm vibe coding I'm relying on that same knowledge and experience to architect the solution rather than deliver it.

    Ive seen the other side- the colleagues who all of a sudden think theyre engineers and are unknowingly exposing critical commercial data to our competitors. That side is scary...and gives me hope that my role while changing, is far from dead.

    Also I have hobbies - i only work to pay for them. If "the man" wants to pay me to spend tokens...fine by me. I'll be here to clean it up if it all goes wrong.

  • source
  • parent
  • hideshow 1 child comment
  • [–] 1 point 6 months ago

    All good, and I respect your perspective!

    I know you were like "flame me!" Lol, But hope I wasn't sounding too judgy. I think it's hard not to have strong opinions on the topic either way these days. (And I'm already prone to soapboxing haha.)

    Wishing you the best out there. :)

  • source
  • parent
  • [–] 4 points 6 months ago* (2 children)

    I recently got moved to another team after my company restructured. Several repos have zero documentation. Most of those don't even have comments on the functions. LinkXxxx(some args) like Xxxx to /what?!/ It's also an over-engineered mess with multiple layers of abstraction. I can't wait to finish figuring out what everything does and re-write (and document it) like a sane person. This code presumably had no AI involvement which I'd argue is even worse since real humans made these shit decisions. Don't get me starting on their testing (and mostly lack thereof)...

    Worker suggested using AI to write some documentation. Another coworker did. I immediately spotted a bunch of hallucinated shit. Good times. I want to know in my head what a thing does, how it works, and how it fits into the architecture. I can't do that if an AI is just deciding stuff; it's like a quiz back in school where I would memorize shit for about one week before 99% of it left my brain forever.

  • source
  • hideshow 2 child comments
  • [–] 2 points 6 months ago (1 child)

    Sometimes documentation doesn't help. My workplace used to be waterfall and we still have systems analysts producing documentation

    One piece of work came to my team as "this calculation fails in this case and we can't tell why"

    Looking at it there were two updates in the documentation showing updates ten years ago the first fixing that corner case with the second fixing a side effect of the fix

    Why didn't it work? It was never built, or perhaps built but never merged

    On the good side we have an excellent plan for how to fix that corner case, on the bad side we aren't funded to do that amount of work so we have to half arse a solution

  • source
  • parent
  • hideshow 1 child comment
  • [–] 1 point 6 months ago

    The documentation I mean here should be in the repo and checked as a part of the PR process. I don't mean it should be a manual, I just mean a readme should at least describe what the service does (it has such a generic name in my case that it's not self-evident and is so broad in scope I don't know what happened). The functions also have terrible naming and no comments to describe what they do. So, as a guy just coming into this team after re-org with no idea what all this stuff does, I was completely lost. They also changed which services which teams owned, further making it difficult to get knowledge.

  • source
  • parent
  • [–] 3 points 6 months ago

    Kill Bill. Wait...

  • source
  • [–] 3 points 6 months ago (2 children)

    So... Just like any other legacy system you inherit.

  • source
  • hideshow 2 child comments
  • [–] 3 points 6 months ago* (1 child)

    I once heard someone describe legacy systems as systems without test coverage. I think it's not the best description, but it's certainly an interesting perspective.

    It's part of why it bothers me when folks say they use LLMs to make unit tests. If anything, you should be writing tests by hands to get a solid specification then let the AI make the code. Of course this is a false dichotomy, but I'm just saying if you have to choose between those two options in some weird hypothetical bizarro world.

  • source
  • parent
  • hideshow 1 child comment
  • [–] 1 point 6 months ago

    Not the best description doesn't cut it, it's just false description. I can easily write a system with 100% test coverage, bugged as hell and containing so many weird abstraction tricks that it takes a significant effort to figure out even what is happening in the simplest scenario. And yes, part of that hundred percent coverage is going to be llm style: test that something does what you already know it does

  • source
  • parent
  • [–] 11 points 6 months ago (1 child)

    Well... Heck. I recently vibe coded an app for a specificish use case. I didn't even think about commenting my code. It was the first time I've ever done such a thing..

    I'll go and comment it all.

    Thanks for the reminder OP

  • source
  • hideshow 1 child comment
  • [–] 5 points 6 months ago

    Woever made this image should learn the difference between line spacing and paragraph spacing…

    This is an example
    of line spacing which
    clearly shows it's together

    And now this is a new
    bit that is separate from
    the above bit

    Readability is important.

  • source
  • [–] 2 points 6 months ago

    And suddenly, I'm reminded of JoCo's "Code Monkey".

  • source
  • [–] 4 points 6 months ago

    The code is the comment anyway. The only thing you should comment is things that are way the hell out in left field about why that bit of code exists when it shouldn't.

  • source
  • [–] 2 points 6 months ago (4 children)

    A lot of the arguments people use against vibe coding sounds a lot like "You shouldn't use a high-level programming language unless you understand the assembly it compiles to."

  • source
  • hideshow 4 child comments
  • [–] 3 points 6 months ago*

    Yes. It's the same thing, except when I joined the market knowing fuck all about computers, while coding with my cute little BASIC commands; there wasn't some tech bro asshole telling all the C programmers that their skills would no longer be required. Or at least he (implicated in Epstein files billionaire, Bill Gates) wasn't saying it quite so loudly (as accused rapist billionaire Sam Altman).

    Incidentally, I still work with that same C programmer, I'm still learning from them, but have since taught them a trick or two; and we both now charge sinful amounts of money for our time.

  • source
  • parent
  • [–] 1 point 6 months ago

    I think I know who did that meme. We had a programmer by that name who did just that.

  • source
  • [–] 1 point 6 months ago (1 child)

    I hate Bills, taking all my money.

  • source
  • hideshow 1 child comment
  • [–] 1 point 6 months ago

    I hate most of the companies paying people to write code though, isn't it a good thing if their code is shit that no one can understand and doomed to collapse under its own weight?

  • source
  • [–] -5 points 6 months ago (3 children)

    Fwiw that's not what vibe coding means

  • source
  • hideshow 3 child comments
  • [+] 9 points 6 months ago (2 children)
  • [–] 1 point 6 months ago* (1 child)

    It means that you created the code via natural language instructions to an LLM as opposed to typing by hand. You still need to verify its work, review and understand the code to at least some extent, and go through many iterations before it's production ready.

    Some people create vibeslop without looking at the code at all which is fine for a throwaway hobby project or personal tools but it will very quickly turn into unmaintainable garbage if you don't guide the architecture, redirect away from bad approaches, review the code carefully and make the LLM fix any issues, ensure proper testing, and periodically refactor and improve code quality. If that sounds like hard work then that's because it is, doing a good job with agentic accelerated engineering is hard work, but you can still build 2x-5x faster at the same quality level than if you typed it by hand. And that's with current models, they're only getting better

  • source
  • parent
  • hideshow 1 child comment
  • load more comments (1 reply)