Robots yes. Humanoid ones? Why? So people can be amazed? Purpose built robots are the future. The human form is sub optimal for most enterprise use cases.
This. I feel like folks are living in two separate worlds. You need to narrow the aperture and take the LLm through discrete steps. Are people just saying it doesn't work because they are pointing it at 1m loc monoliths and trying to oneshot a giant epic?
its all fake coverage, for fake tests, for fake OKRs
what are people actually getting done? I've sat next to our top evangelist for 30 minutes pair programming and he just fought the tool saying something was wrong with the db while showing off some UI I dont care about.
like that seems to be the real issue to me. i never bother wasting time with UI and just write a tool to get something done. but people seem impressed that AI did some shitty data binding to a data model that cant do anything, but its pretty.
it feels weird being an avowed singularitarian but adamant that these tools suck now.
Working code doesn’t mean the same for everyone. My coworker just started vibe coding. Her code works… on happy paths. It absolutely doesn’t work when any kind of error happens. It’s also absolutely impossible to refactor it in any way. She thinks her code works.
The same coworker asked to update a service to Spring Boot 4. She made a blog post about. She used LLM for it. So far every point which I read was a lie, and her workarounds make, for example tests, unnecessarily less readable.
So yeah, “it works”, until it doesn’t, and when it hits you, that you need to work more in sum at the end, because there are more obscure bugs, and fixing those are more difficult because of terrible readability.
I can't help but think of my earliest days of coding, 20ish years ago, when I would post my code online looking for help on a small thing, and being told that my code is garbage and doesn't work at all even if it actually is working.
There are many ways to skin a cat, and in programming the happens-in-a-digital-space aspect removes seemingly all boundaries, leading to fractal ways to "skin a cat".
A lot of programmers have hard heads and know the right way to do something. These are the same guys who criticized every other senior dev as being a bad/weak coder long before LLMs were around.
Parent's profile shows that they are an experienced software engineer in multiple areas of software development.
Your own profile says you are a PM whose software skills amount to "Script kiddie at best but love hacking things together."
It seems like the "separate worlds" you are describing is the impression of reviewing the code base from a seasoned engineer vs an amateur. It shouldn't be even a little surprising that your impression of the result is that the code is much better looking than the impression of a more experienced developer.
At least in my experience, learning to quickly read a code base is one of the later skills a software engineer develops. Generally only very experienced engineers can dive into an open source code base to answer questions about how the library works and is used (typically, most engineers need documentation to aid them in this process).
I mean, I've dabbled in home plumbing quite a bit, but if AI instructed me to repair my pipes and I thought it "looked great!" but an experienced plumber's response was "ugh, this doesn't look good to me, lots of issues here" I wouldn't argue there are "two separate worlds".
> It shouldn't be even a little surprising that your impression of the result is that the code is much better looking than the impression of a more experienced developer.
This really is it: AI produces bad to mediocre code. To someone who produces terrible code mediocre is an upgrade, but to someone who produces good to excellent code, mediocre is a downgrade.
Today. It produces mediocre code today. That is really it. What is the quality of that code compared to 1 year ago. What will it be in 1 year? Opus 6.5 is inevitable.
That's what they've been saying for years now. Seems like the same FSD marketing. Any day now it'll be driving across the country! Just you wait! -> Any day now it'll be replacing software developers! Just you wait! Frankly, the same people who fell for the former are falling for the latter.
Rather, to me it looks like all we're getting with additional time is marginal returns. What'll it be in 1 year? Marginally better than today, just like today is marginally better compared to a year ago. The exponential gains in performance are already over. What we're looking at now is exponentially more work for linear gains in performance.
You think it'll rapidly get smarter, but it just recreates things from all the terrible code it was fed.
Code and how it is written also rapidly changes these days and LLMs have some trouble drawing lines between versions of things and the changes within them.
Sure, they can compile and test things now, which might make the code work and able to run. The quality of it will be hard to increase without manually controlling and limiting the type of code it 'learns' from.
Except I work with extremely competent software engineers on software used in mission critical applications in the Fortune 500. I call myself a script kiddie because I did not study Computer Science. Am I green in the test run? Does it pass load tests? Is it making money? While some of yall are worried about leaky abstractions, we just closed another client. Two worlds for sure where one team is skating to the puck, looking to raise cattle while another wants to continue nurturing an exotic pet.
Plenty of respect to the craft of code but the AI of today is the worst is is ever going to be.
Can you just clarify the claim you're making here: you personally are shipping vibe coded features, as a PM, that makes it into prod and this prod feature that you're building is largely vibe coded?
It depends heavily on the scope and type of problem. If you're putting together a standard isolated TypeScript app from scratch it can do wonders, but many large systems are spread between multiple services, use abstractions unique to the project, and are generally dealing with far stricter requirements. I couldn't depend on Claude to do some of the stuff I'd really want, like refactor the shared code between six massive files without breaking tests. The space I can still have it work productively in is still fairly limited.
That's a significant rub with LLMs, particularly hosted ones: the variability. Add in quantization, speculative decoding, and dynamic adjustment of temperature, nucleus sampling, attention head count, & skipped layers at runtime, and you can get wildly different behaviors with even the same prompt and context sent to the same model endpoint a couple hours apart.
That's all before you even get to all of the other quirks with LLMs.
Na. Most successful startups don't worry about super tight code up front and hack the shit out of something and support tens of thousands of user with completely garbage code and architecture.
I know this because I am at one now making an ungodly amount of money with 50k active users a day on a complete mudball monothilic node + react + postgres app used by multiple Fortune 100 companies.
Having said that, I have become a lot better at being direct these past few years, so I'd likely just say "I'm not able to, sorry. I can recommend some good hotels though".
Default No is fine, just go with it. That’s a huge ask. It was a 2 week stay, that’s a hell no unless you’re my nuclear family then maybe we can discuss it. Even then, there’s some family I don’t want as overnight guests and I usually put up in a nearby hotel when they visit.
No reason to feel guilty saying no when the ask is that large. I feel bad sometimes saying no to small things. Because it’s trivial on the surface and I don’t have a good reason for saying no except I just don’t want to do it. In any case, I like treating no as my default answer to everything then I have to be convinced to say yes (even if it’s a quick internal negotiation with myself).
If you’re consistent, the most abusive askers learn not to ask. The ones that ask with expectations of a yes, the ones that try to make you feel bad for saying no, those people go away. And that’s my ideal position, I’m only being asked for reasonable things so actually end up saying yes more often than I say no.
The askers who make you feel bad don't go away. They go up your org chart or get replaced by similar if your company culture tolerates it. You're the one who goes away or settles.
You are responsible for your feelings and setting your boundaries.
Learning how to set boundaries is something most people learn as they mature. Yeah, not easy. I have especially noticed recently that some of my friends who are mums have learnt how to claim their own needs only after their kids have left home. Some people give too much.
Do you expect others to adivinate what your personal boundaries are?
Do you get frustrated when friends or family make the wrong assumptions?
If you have arseholes in your life that actually make you feel bad, then it is even more important to learn how set boundaries with them. If they don't respect the boundaries you set, or create conflict, then that is often very difficult to resolve.
I struggle with conflict avoiders because they have needs however they often act passive. Yet their hidden expectations remain, and their response if you fail to meet their expectations is often poor. One friend in particular also often guesses wrong to my detriment, instead of asking a simple question.
Do mind readers want others to read minds?
I strongly dislike passive people that blame others for their poor communications.
> I strongly dislike passive people that blame others for their poor communications.
Same. I struggle with the construct specifically because I think I am both an asker and a guesser. I do agree it exists however I can’t bucket myself into either side. The approach I choose to utilize at any given time is a contextual calculation. Do I have a strong opinion? Do I have a sufficient status to assert myself? Do I not care and just want to appease the other person? Do I intentionally want to stroke their ego?
But, choose an approach and use it as a tool. Miscalculations occur leading to outcomes I may not predict or prefer sometimes but that’s just a learning experience for me. I might adjust my internal algorithm for making that calculation in the future. I might decide I just don’t like interacting with that person, and that’s fine too. But I don’t blame anyone or expect them to change for me.
Did you mean to reply to someone else? I don't know where this is coming from as I didn't make these claims.
That said, your comment is disturbing.
It's a obnoxious to "strongly dislike" (read: hate) people who don't have resilient self-esteem. It lacks compassion. And if someone's bullying you, getting platitudes about "responsible for your feelings" and "boundaries" is useless.
Strongly dislike can also mean you just prefer to avoid those people or limit your interactions. It doesn’t mean hate.
If you want people like this to stop avoiding you, it’s an internal adjustment that needs to be made. That’s the responsibility for yourself part. Ignoring you is not hurting the other person one bit, actually they are benefiting from it as they skip dealing with your personality they dislike. It’s not to say they are biased against you, if you were more compatible they may change their stance without thinking about it. That wouldn’t happen if they hated you.
Hate is a strong dislike but that doesn’t mean a strong dislike is hate.
It could mean anything more. Especially given the medium we’re using to communicate, where they chose those words instead of just saying hate. This medium is concise and those words were chosen over the word hate. I think it’s most likely they were chosen to reference to the huge grey area of stuff they could have meant but they didn’t want to explain due to their desire for to keep concise text communications which is what we’re all engaging with online. If we had to explain why we chose every word we chose this mode of communication would be useless.
It's not mind reading. It's basic empathy and respect. Expecting others to understand the norms of social behavior is not smart, but it is perfectly normal. Realizing that many people lack the ability to empathize or socialize politely and dealing with that is an unfortunate consequence of modern society making travel so easy. We're all mixed up and people from totally different cultures need to learn to deal with each other.
If someone goes on to say, "well you ruined my vacation" or something like that, they weren't asking at all, they were demanding and now they're bullying you about having boundaries to try to tear your boundaries down.
People who go out of their way to try to trample your explicitly stated boundaries are abusing you.
So say no, and if they don't take it well, create distance or tell them off. Avoiding conflict in this case is fully to your own detriment.
If, on the other hand, they do take it well, then guess what? They're an asker and are just fully exploring their options and it's no big deal to them that you said no.
That is reductive, why not call all everything CGI then? Or call CGI pixel art as well? As we’re talking about “art”, it’s necessarily going to be subjective, but pixel art has certain style aspects such as use of 2x1 lines (https://www.the-pixel-artist.com/articles/top-ten-things-new...). This is just an example, while I’m not saying that every convention must be met in order to qualify as pixel art, not having any doesn’t make a useful definition of a genre.
reply