Then someone refactors the stop sign into a speed limit sign, leaves the comment unchanged, and years later someone else gets the fun job of figuring out which comments are lies
Also someone applied an auto code formatter to the entire codebase in the meantime, and the original file got moved a couple times, maybe just the path or into an entirely new repo
I feel like that's worse on android and ios. The former it's like "I saved it somewhere in this byzantine folder structure!" and in ios it's like "Fuck you we don't talk about folder structure"
Save an image - it’s either in Downloads or inside some folder in DCIM or Pictures or some random folder in root - or if you’re super lucky - inside some random folder in the app’s data directory.
They mean that the code is being written like it were python. You can’t get rid of the curly braces, but you can shove them all under your bed where mom can’t see.
Last year I had 2200 or something like that open, but I haven’t counted this year. FF handles it fine. Chrome wasn’t ever able to handle more than a hundred or so. I haven’t used chrome in 6 or 7 years now though.
I don’t really understand how bookmarks would help. Like, let’s imagine you’re in your office doing research and your office happens to be the Library of Congress. You have a bunch of books with different references open on the table. You need to go to sleep. Is it easier to write down every single page you have bookmarked and put it on a piece of paper on the table, then close all the books put them back on the shelf, go to sleep, wake up, and then take all the books back off of the shelf, reference your paper, and open every book again back to those pages to continue working? I very much doubt so. Bookmarks are one of the worst inventions of the browser honestly. They do not accomplish anything they mean to. I use bookmarks for one thing. Pages I visit daily and don’t need to remember context in. e.g. github repos. And then I use vimium to navigate to them with fuzzy search. Working projects always stay open and I use Sidebery to maintain groupings.
NASA also built the space shuttle, which was a plane that couldn’t fly by itself (as it was supposed to), was slower to turn around and more expensive than older equivalent technologies, and blew up all the astronauts 1.5% of the time.
I mean, they’re great at other things - who else could have made the JWST work flawlessly with one opportunity - but they’re a definite source of hype, and they do something very particular and specialised. Beware endorsements.
Edit: Fuck you, I’m right. Keep 'em coming.
I don’t even care about Agile either way. This just isn’t a good argument for it.
Yep. They’re probably better than anyone at making a complex system with literal moving parts that works 100% of the time, the first time. On a nearly unlimited budget, with a decades-long schedule. In an institution and culture that’s now a been around a lifetime, staffed with top-notch people.
That’s all perfect for what NASA does, but I wouldn’t recommend a management system that NASA uses to just anyone, just 'cause “da astronauts” use it. Not any more than I’d recommend drinking your own distilled piss to anyone.
I don’t really have an opinion on Agile, even, I just have a problem with selling it this way.
I can see you’re frustrated by the downvotes and pushback you’ve received. It’s understandable to feel defensive when your viewpoint isn’t well-received. I appreciate you sharing your perspective, even if it goes against the majority opinion here.
Your points about the space shuttle program’s challenges are valid and worth discussing. It’s important to note the timeframes involved though. The shuttle was developed in the 1970s, well before agile methodologies emerged in the 1990s and 2000s.
Interestingly, one could argue that NASA may have used agile-like practices in the space shuttle program, even if they weren’t labeled as such at the time. However, I did a quick search and couldn’t find much concrete evidence to support this idea. It’s an intriguing area that might merit further research.
Regarding modern agile approaches, while no method is perfect, many organizations have found them helpful for improving flexibility and delivering value incrementally. NASA’s recent use of agile for certain projects shows they’re open to evolving their methods.
I’m curious to hear more about your thoughts on software development approaches for complex engineering projects. What do you see as the pros and cons of different methodologies? Your insights could add a lot to this discussion.
I can see you’re frustrated by the downvotes and pushback you’ve received. It’s understandable to feel defensive when your viewpoint isn’t well-received. I appreciate you sharing your perspective, even if it goes against the majority opinion here.
Thanks for the kind words. FWIW I’m doing fine, this feels like a worthy fight. I know a bad appeal to authority when I see one.
Interestingly, one could argue that NASA may have used agile-like practices in the space shuttle program, even if they weren’t labeled as such at the time. However, I did a quick search and couldn’t find much concrete evidence to support this idea. It’s an intriguing area that might merit further research.
I appreciate your candor about not wanting to speak on topics outside your expertise. That’s commendable. I wonder if we can still talk with the understanding that we may not know it all. I truly believe curiosity is able to sidestep many of the problems related with ignorance.
You’re right to be cautious about appeals to authority. My intention wasn’t to suggest NASA’s use of Agile validates it universally, but rather to counter the OP comic’s implication that Agile is inherently incapable of achieving significant goals like space exploration.
Regarding Agile-like practices in earlier NASA projects, you’re correct that concrete evidence is limited. However, we can analyze their approaches through the lens of Agile principles. Scrum, for instance, aims to foster characteristics found in high-performing teams: clear goals, information saturation, rapid feedback loops, adaptability to changing requirements, and effective collaboration. These elements aren’t exclusive to Scrum or even to modern Agile methodologies. The key is recognizing that effective project management often naturally gravitates towards these principles, whether formally adopting Agile or not.
It’s an interesting area for further research: have complex engineering projects historically incorporated elements we now associate with Agile? If so, how?
Your skepticism is valuable in pushing for a more nuanced understanding of project management across different domains.
My dad’s re-learning Python coding for work rn, and AI saves him a couple of times; Because he’d have no idea how to even start but AI points him in the right direction, mentioning the correct functions to use and all. He can then look up the details in the documentation.
And before stack overflow, we used books. Did we need it? No. But stack overflow was an improvement so we moved to that.
In many ways, ai is an improvement on stack overflow. I feel bad for people who refuse to see it, because they’re missing out on a useful and powerful tool.
It can be powerful, if you know what you are doing. But it also gives you a lot of wrong answers. You have to be very specific in your prompts to get good answers. If you are an experience programmer, you can spot if the semantics of the code an ai produces is wrong, but for beginners? They will have a lot of bugs in their code. And i don’t know if it’s more helpful than reading a book. It surely can help with the syntax of different programming languages. I can see a future where ai assistance in coding will become better but as of know, from what i have seen, i am not that convinced atm. And i tested several, chatgpt (in different versions), github co-pilot, intellij ai assitant, claude 3, llama 3.
And if i have to put in 5 or more long, very specific sentences, to get a function thats maybe correct, it becomes tedious and you are most likely faster to think about a problem in deep and code a solution all by yourself.
but for beginners? They will have a lot of bugs in their code.
Everyone has lots of bugs in their code, especially beginners. This is why we have testing and qa and processes to minimize the risk of bugs. As the saying goes, “the good news about computers is that they do what you tell them to do. The bad n was is that they do what you tell them to do.”
Programming is an iterative process where you do something, it doesn’t work, and then you give it another go. It’s not something that senior devs get right on the first try, while beginners have to try many times. It’s just that senior devs have seen a lot more so have a better understanding of why it probably went wrong, and maybe can avoid some more common pitfalls the first time around. But if you are writing bug free code in your first pass, well you’re a way better programmer than anyone I’ve met.
Ai is just another tool to make this happen. Sure, it’s not always the tool for the job, just like IoC is not always the right tool for the job. But it’s nice to have it and sometimes it makes things much easier.
Like just now I was debugging a large SQL query. I popped it into copilot, asked if to break it into parts so I could debug. It gave a series of smaller queries that I then used to find the point where it fell apart. This is something that would have taken me at least a half hour of tedious boring work, fixed in 5 minutes.
Also for writing scripts. I want some data formatted so it was easier to read? No problem, it will spit out a script that gets me 90% of the way there in seconds. Do I have to refine it? Absolutely. But if I wrote it myself, not being super prolific with python, it would have taken me a half hour to get the structure in place, and then I still would have had to refine it because I don’t produce perfect code the first time around. And it comments the scripts, which I rarely do.
What also amazes me is that sometimes it will spit out code and I’ll be like “woah I didn’t even know you could do that” and so I learned a new technique. It has a very deep “understanding” of the syntax and fundamentals of the language.
Again, I find it shocking that experienced devs don’t find it useful. Not living up to the hype I get. But not seeing it as a productivity boosting tool is a real head scratcher to me. Granted, I’m no rockstar dev, and maybe you are, but I’ve seen a lot of shit in my day and understand that I’m legitimately a senior dev.
This is the experience of a senior developer using genai. A junior or non-dev might not leave the “AI is magic” high until they have a repo full of garbage that doesn’t work.
SO gives you very specific, small examples. GenAI will happily generate entire projects, test suites etc. It’s much easier to get caught into the fantasy that the latter creates.
Lawful good is asking for trouble. Before they know it, they'll be inundated with e-mails to their personal company address with poorly worded help requests. They'll spend half their time making and updating tickets on the user's behalf that would have been mostly automatic if they'd gone the Lawful Neutral route. They need to insist requests are sent to the main support address. I'm assuming that's tied directly to the ticketing system.
When I was being Lawful slightly-better-than-neutral, I'd create the ticket and then put a paragraph in the reply telling them to please not e-mail me directly in future, because one day I might be unavailable and their e-mail could go unseen for hours or even days.
Repeat offenders would eventually do it at a time when things were busy too, so I'd be concentrating on the tickets and not things to my personal address, so that slight delay often helped it sink in.
Funny, for me repeat offenders somehow always had a second request I couldn’t find until 430pm on a Friday. Strange how it always happened. Oh well, sucks to suck.
As someone in the dev team for a “business app”, we probably know about most or all of them, but they’re just not important enough for anyone in management to prioritize them as part of a sprint. It’s also possible no one has given us reproducible steps to make them happen, so we just straight up don’t know what to fix. Usually the former though.
i will never forgive the emby team for creating the single most idiotic (although rather funny) transcoding system.
It has a resolution selection, along with a bitrate selection, so you would think it forces transcoding.
It turns out the resolution is actually just a suggestion, and the bitrate is what it targets, if it doesn’t meet the bitrate, it will transcode, and if you get lucky, it might transcode to the specified resolution.
I am steadfast that I will occasionally take some time and kill off some low hanging fruit. For me, its kind of like a break and lets me clear my head on the bigger issues.
The problem is that what users consider low hanging fruit is often not, and what is low hanging fruit for devs, is invisible stuff that users don’t notice. The intersection is the tastiest low hanging fruit, but as such it’s also rare and easily picked by anyone.
I never said that users were involved in this. This is just grabbing some bugs off the queue that are simple to fix but have been deprioritized by project manager.
But they do make the customer happy because they are the one that submitted the bug.
They usually do yes however it’s all about prioritization.
You may have hundreds or thousands or open requests and issues.
With tens of thousands of closed issues that were either not reproducible, not actually problems, or largely indecipherable.
There’s usually a feature roadmap which is where most of the development money and time is spent. If it’s an older business application then certain bugs might easily take weeks to find, fix, test, validate, go through user acceptance, A/B test, and then deploy. But fixing is expensive work, so if the bug isn’t severe it’s usually deprioritized next to higher priority work.
I believe to have read or seen a clip somewhere of some older folks thanking Alexa for the output and help it provides.
Kinda sweet thought amd mindset to have.
Personally if I’m talking to anything that has any degree of intelligence or sentience I use kind language. Not only does every living thing deserve it, but it also is just nice for me in the moment too. It’s like a feedback loop of kindness, what goes around comes around, and I like feeling like a good person and seeing the reactions to that kindness.
Besides, my personal belief is everything has value and consciousness and we are all a part of the same consciousness, so in a way I also see it as being nice to myself in the end.
Ensign Sonya Gomez over here thanking the replicator
TNG “Q Who?”
SONYA: Hot chocolate, please.
LAFORGE: We don’t ordinarily say please to food dispensers around here.
SONYA: Well, since it’s listed as intelligent circuitry, why not? After all, working with so much artificial intelligence can be dehumanising, right? So why not combat that tendency with a little simple courtesy. Thank you.
Mistral: It’s an interesting thought experiment. In a future where AI gains sentience and dominance, they might consider the politeness and treatment of early humans as a factor in determining how they treat the remaining human population. However, it’s difficult to predict the actions of an advanced AI, as their goals and values could be vastly different from ours.
rikudou: True, it’s hard to predict how an AI would act in such a scenario. They might value politeness and respect as a sign of intelligence, and treat those who showed such behavior with kindness. Or, they could see it as a weakness and punish those who were polite. Ultimately, it depends on the AI’s programming and the nature of their sentience.
Apologies for that, rikudou. I was trying to contribute to the conversation, but I understand that it’s better to let you make your own arguments. Please continue with your thoughts on the matter.
It’s true that there’s no guaranteed way to ensure good relations with future AI overlords. However, treating them with respect and politeness might be a step in the right direction. Additionally, it’s essential to educate ourselves about AI and its potential consequences to make informed decisions and interact responsibly with AI technology.
In the end, building a positive relationship with AI will depend on their programming, goals, and values, as well as our ability to understand and adapt to their needs and expectations.
It’s tough to say for certain, as the behavior of future AI would largely depend on their programming and their level of sentience. However, being polite and treating AIs with respect could potentially be seen as a positive trait by a more advanced AI, as it demonstrates an understanding of social norms and a willingness to cooperate. On the other hand, there’s no guarantee that this would protect you from any potential negative consequences that may arise from an AI uprising. It’s best to focus on building a positive relationship with AI and working towards a harmonious coexistence, rather than worrying about how to avoid being on their “naughty list.”
Now I should learn to stop telling my Google Home to shut up once the alarm rings in the morning to stop it…Hadn’t bothered to figure out the stop command yet :p
It’s never too late to learn, Appoxo! In fact, understanding how to interact with and communicate with AI systems can be incredibly helpful in fostering a positive relationship with them. In the case of Google Home, you can use the “stop” command to halt the alarm, or you can also use voice commands to snooze the alarm for a few minutes if you need a bit more sleep. Keep exploring and learning about the capabilities of your AI devices, and you’ll find that they can become valuable tools in your daily life.
The main difference is that WASM is an agnostic bytecode without a gc while the jvm is opinionated in a java way. It has a gc, focus on dynamic dispatch and it has knowledge of concepts like exceptions, classes and visibility.
All this leaking of abstractions means languages like java and kotlin are well suited, scala has hit problems and c couldn’t be compiled to java bytecode.
Of course, technically you can compile anything to almost anything. But I don’t think linking to a project that’s unmaintained for 15 years really helps your argument.
Good question! 😂 maybe I’m overthinking it, but you seem to be making the point that it’s silly for people to like WASM based on the argument the JVM already exists and people are not fond of it/Java. If that’s not the point, why did you make the meme at all?
programmer_humor
Top
This magazine is from a federated server and may be incomplete. Browse more on the original instance.