I guess prepare for potential kernel rot: https://www.neowin.net/news/linus-torvalds-declares-massive-ai-fueled-code-surges-as-the-new-normal-for-linux/
isn’t it fun how every major operating system is vibe coded now
windows is an unstable mess, macos’s new ui is the most broken it’s been in decades, and linux is getting one new vulnerability per day. the future is exciting!
It will make the cyberpunk hacking easier I guess.
The vulnerabilities were always there, one of the better uses of AI has been to find them.
I love tech. My brain loves soaking up new things. Currently writing my first ever game engine in my 50s in c with my kid based on books and include files. Better late than never.
The technology was never the problem. It’s the money people. Always was. The Marxists got that bit right. Some of the tech bros are from a tech background but their culture and motivations aren’t like mine.
The money person these days follows the drug pusher/pimp model. They want to control you and have you on a hook. Everything has gaming machine mechanisms built in to keep you coming back. You can’t walk away. They have all your data, all your connections. You are helpless. A victim, but you walked right into it. Final victory for them is to lobotomise all your higher order thinking skills. Your just a body to lie there and be fucked.
The “correct” way to use AI for coding (and anything really) is to ask for explanations / tutorials when you can’t find one online, then learn from that.
Never let it do something for you. That’s how you lose. If you’re not actively learning, you’re actively rotting, and that goes for life in general too.
The “correct” way to use AI for coding (and anything really) is to ask for explanations / tutorials when you can’t find one online, then learn from that.
except the “explanation” frequently will be 100% “hallucinated” bullshit
That’s why I always ask it to cite sources. Basically googld ATP since google is turning to shit and all other search engines still aren’t quite as good
It could very easily use a completely different or hallucinated source.
But a lot of LLM products are now providing source links right in the response. I’ve found them useful, and hopefully they aren’t produced just by feeding the text back in and asking for a link.
That’s exactly how those links are produced.
For what it’s worth, I’ve been working on (yet another) ActivityPub based micro blogging application and LLMs have been enormously helpful and so far as I can tell, correct. Often it cites the AP specs and its extensions, as well as specific implementations from existing major AP apps. It can show me expected outputs, what responses from my app should look like in response to different requests from other servers, and quickly give context for features like Mastodon’s shared inbox. I’m not having it simply generate code, but I think I’m still moving way faster than I otherwise could. I don’t recall it ever giving me incorrect information.
It’s the first time I’ve used an LLM as a tool this way, and I’m pretty impressed with it. I’m using the assistant made available through Kagi.
Often it cites the AP specs and its extensions
Tip: check those citations yourself before publishing with your name on the product. Yeah, they’re usually correct - do you only usually not want to be perceived as a lazy idiot?
I get that. I wouldn’t publish the code anywhere until an alpha is more or less ready and pretty well tested, and yes, I understand the importance of making sure it behaves in an expected, performant and pro-social manner with the existing compatible fediverse apps.
I’m not too worried about it, but thanks for your genuine concern about my reputation. ;) Since I’m the one writing the code, I’m more worried about the quality of that, if anything.
What you said is fine for people learning, but there’s nothing wrong with having AI do something for you when you’ve done it a hundred times and don’t want to do it again. Some of us are actually out here working, not just learning.
We already invented a tool for that, it’s called a library.
I don’t think that’s a good idea, if you can’t find an explanation online that means that there’s not much info available in which case the best thing would be to ask on a forum, that way other people that look for that info will find it.
Not really, google results have been just that bad for the last 10 years. I can spend 10min looking for a piece of documentation on something and not find it. Or I can prompt an internet-connected AI and have it spit out links to relevant docs. It’s gotten THAT bad.
The main problem here are the software developers who don’t notice their brain rot.
Self awareness is all too rare.
Developers who are told to use AI whether they like it or not, however, tell a different story.
Well there’s the problem.
I’m a software developer and I say that AI is the greatest force-multiplier that’s been introduced into the field since the compiler. I love using it, it handles the most tedious and annoying parts of the process. But there are situations I don’t want to use it in, and of course being forced to use would give me a more negative opinion of it. Obviously.
people shit down your throat and you celebrate and beg for more. Absolute clownshow.
In the late 1980s there was a time where we seriously weighed the option of hand assembly vs using compilers and hand assembly didn’t always lose. In the early 1990s I wanted to use C++ but the available compiler for IBM compatible PCs was too buggy to be of value.
By the mid 1990s that had changed, good C compilers were exceeding all but the highest effort human assembly code - if you didn’t like how it looked in assembly, you could much more easily “fix it” with a tweak to the C code instead of the assembly. I feel like we’re sort of getting there with AI agent LLMs today - if you don’t like what it provided, tell it why and let it try again - it’s usually faster and easier and gets a better product for the time invested to use the tool instead of calling it a slop box and doing it yourself.
There isn’t any credible evidence out there that actually shows LLMs are a “force multiplier.” That is almost certainly just a made up marketing term for unprofitable chatbot companies.
‘Your personal experience is invalid because it goes against the circlejerk’
Did you miss the part about no credible evidence? Feeling like something is a certain way doesn’t make it true.
If it’s a tool you can use yourself and it makes you more efficient, you don’t need a study to recognize its efficiency.
If you’re a software engineer, just try it yourself. Your own experience is the best proof you can find to judge if a tool is useful to you or not.
I’m a software developer and I say that AI is the greatest force-multiplier that’s been introduced into the field since the compiler.
As a person who works with coworkers who fully embraced it, it doesn’t look like they are any faster. There is one group that is faster, but they don’t verify their code and provide burden of it on another person who reviews PR to go through their shit code (sorry, but it is unnecessarily complex, does things in weird ways, I’ve seen it had bugs that even canceled each other (I guess this is probably due to re-running until things work))
I’ve seen it had bugs that even canceled each other (I guess this is probably due to re-running until things work))
I’ve seen human coders do this quite a bit, even myself - always unintentional, usually brain-bending when you find the first inversion.
I think it is domain of young developers who just want choice to do what they do, but don’t care how.
Even you use LLM you often have similar mindset.
I belong to group of people with a weakness that I want to understand every step of the code that I produce. When LLM produces something I need to understand what it does (which takes time) then I realize I could do it better way, so I rewrite it. So LLM just slows me down.
I understand many things clearly, but when it comes to binary yes/no true/false 1/0 type results my brain tends to answer: Yes, it’s one of those. I don’t think I’ve made a double inversion “working” error since the 1990s, but I know I’ve seen others do it - even in Rust.
