- cross-posted to:
- [email protected]
You must log in or register to comment.
Bonus points if the attackers use ai to script their attacks, too. We can fully automate the SaaS cycle!
That is the real dead Internet theory: everything from production to malicious actors to end users are all ai scripts wasting electricity and hardware resources for the benefit of no human.
That would only happen if we give power to our ai assistants to buy things on our behalf, and manage our budgets. They will decide among themselves who needs what and the money will flow to billionaires pockets without any human intervention. If humans go far enough, not even rich people would be rich, as trust funds, stock portfolios would operate under ai. If the ai achieves singularity with that level of control, we are all basically in spectator mode.
Seems like a fitting end to the internet, imo. Or the recipe for the Singularity.
I am not a bot trust me.
Not only internet. Soon everybody will use AI for everything. Lawyers will use AI in court on both sides. AI will fight against AI.
they’ll find a use case any day now for realsies.
It was a time of desolation, chaos, and uncertainty. Brother pitted against brother. Babies having babies.
Then one day, from the right side of the screen, came a man. A man with a plastic rectangle.
lol thanks
I was at a coffee shop the other day and 2 lawyers were discussing how they were doing stuff with ai that they didn’t know anything about and then just send to their clients.
That shit scared the hell out of me.
And everything will just keep getting worse with more and more common folk eating the hype and brainwash using these highly incorrect tools in all levels of our society everyday to make decisions about things they have no idea about.
I’m aware of an effort to get LLM AI to summarize medical reports for doctors.
Very disturbing.
The people driving it where I work tend to be the people who know the least about how computers work.
This is the opposite of the singularity
It is a singularity, in the sense that it is an infinitely escalating level of suck.
I never said it was going to be any good!
Suckularity?
The Internet will continue to function just fine, just as it has for 50 years. It’s the World Wide Web that is on fire. Pretty much has been since a bunch of people who don’t understand what Web 2.0 means decided they were going to start doing “Web 3.0” stuff.
The Internet will continue to function just fine, just as it has for 50 years.
Sounds of intercontinental data cables being sliced
Someone really should’ve replied with
My attack was built with Curson
This is what happens when you don’t know what your own code does, you lose the ability to manage it, that is precisely why AI won’t take programmer’s jobs.
I don’t need ai to not know what my code does
but with AI you can not know even faster. So efficient
You are even freeing up the space that was needed to comprehend and critically think
More space to keep up with the latest brainrot10x it!!!
AI can be incredibly useful, but you still need someone with the expertise to verify its output.
Managers hoping genAI will cause the skill requirements (and paycheck demand) of developers to plummet:
Also managers when their workforce are filled with buffoons:
Reminds me of the days before ai assistants where people copy pasted code from forums and then you’d get quesitions like “I found this code and I know what every line does except this ‘for( int i = 0; i < 10; i ++)’ part. Is this someone using an unsupported expression?”
I’m less knowledgeable than the OOP about this. What’s the code you quoted do?
It’s a standard formatted for-loop. It’s creating the integer variable i, and setting it to zero. The second part is saying “do this while i is less than 10”, and the last part is saying what to do after the loop runs once -‐ increment i by 1. Under this would be the actual stuff you want to be doing in that loop. Assuming nothing in the rest of the code is manipulating i, it’ll do this 10 times and then move on
I would also add that usually i will be used inside the code block to index locations within whatever data structures need to be accessed. Keeping track of how many times the loop has run has more utility than just making sure something is repeated 10 times.
It’s a for loop. Super basic code structure.
@[email protected] posted a detailed explanation of what it’s doing, but just to chime in that it’s an extremely basic part of programming. Probably a first week of class if not first day of class thing that would be taught. I haven’t done anything that could be considered programming since 2002 and took my first class as an elective in high school in 2000 but still recognize it.
for( int i = 0; i < 10; i ++)This reads as “assign an integer to the variable
Iand put a 0 in that spot. Do the following code, and once completed add 1 toI. Repeat untilIreaches 10.”Int
I= 0 initiatesI, tells the compiler it’s an integer (whole number) and assigns 0 to it all at once.I++ can be written a few ways, but they all say “add 1 to I”I< 10 tells it to stop at 10For tells it to loop, and starts a block which is what will actually be looping
Edits: A couple of clarifications
i <= 9, you heathen. Next thing you’ll do isi < INT_MAX + 1and then the shit’s steaming.I’m cooked, see thread.
If it was correct it wouldn’t have been copied into the forums lmao
I mean
i < 10isn’t wrong as such, it’s just good practice to always use<=because in theINT_MAXcase you have to and everything should be regular because principle of least astonishment: That10might become a, that then might become, each of those changes look valid in isolation but if there’s only a singlei < FOOin your codebase you introduced a bug by spooky action at a distance. (overflow on int is undefined behaviour in C, in case anyone is wondering what the bug is).…never believe anyone who says “C is a simple language”. Their code is shoddy and full of bugs and they should be forced to write Rust for their own good.
But your case is wrong anyways because
i <= INT_MAXwill always be true, by definition. By your argument<is actually better because it is consistent from< 0to iterate 0 times to< INT_MAXto iterate the maximum number of times.INT_MAX + 1is the problem, not<which is the standard to write for loops and the standard for a reason.You’re right, that’s what I get for not having written a line of C in what 15 years. Bonus challenge: write
for i in i32::MIN..=i32::MAXin C, that is, iterate over the whole range, start and end inclusive.(I guess the
..=might be where my confusion came from because Rust’s..is end-exclusive and thus like<, but also not what you want becausei32::MAX + 1panics).for (int i = INT_MIN; ; i++) { ... if (i == INT_MAX) break;}Would you be bold enough to write
if (i++ == INT_MAX) break? The result of the increment is never used, but an increment is being done, at least syntactically, and it overflows, at least theoretically, so maybe (I’m not 100% sure) the compiler could be allowed to break out into song because undefined behaviour allows anything to happen.
<=makes sense if you start from 1.
This is satire / trolling for sure.
LLMs aren’t really at the point where they can spit out an entire program, including handling deployment, environments, etc. without human intervention.
If this person is ‘not technical’ they wouldn’t have been able to successfully deploy and interconnect all of the pieces needed.
The AI may have been able to spit out snippets, and those snippets may be very useful, but where it stands, it’s just not going to be able to, with no human supervision/overrides, write the software, stand up the DB, and deploy all of the services needed. With human guidance sure, but with out someone holding the AIs hand it just won’t happen (remember this person is ‘not technical’)
It’s further than you think. I spoke to someone today about and he told me it produced a basic SaaS app for him. He said that it looked surprisingly okay and the basic functionalities actually worked too. He did note that it kept using deprecated code, consistently made a few basic mistakes despite being told how to avoid it, and failed to produce nontrivial functionalies.
He did say that it used very common libraries and we hypothesized that it functioned well because a lot of relevant code could be found on GitHub and that it might function significantly worse when encountering less popular frameworks.
Still it’s quite impressive, although not surprising considering it was a matter of time before people would start to feed the feedback of an IDE back into it.
Did it provision a scalable infrastructure? Because that’s the aaS part of SaaS.
I assume not, but we didn’t discuss that
Mmmmmm no, Claude definitely is. You have to know what to ask it, but I generated and entire deadman’s switch daemon written in go in like an hour with it, to see if I could.
So you did one simple program.
SaaS involves a suite of tooling and software, not just a program that you build locally.
You need at a minimum, database deployments (with scaling and redundancy) and cloud software deployments (with scaling and redundancy)
SaaS is a full stack product, not a widget you run on your local machine. You would need to deputize the AI to log into your AWS (sorry, it would need to create your AWS account) and fully provision your cloud infrastructure.
Lol they don’t need scaling and redundancy to work. They just need scaling and redundancy to avoid being sued into oblivion when they lose all their customer data.
As a full time AI hater, I fully believe that some code-specialized AI can write and maybe even deploy a full stack program, with basic input forms and CRUD, which is all you need to be a “saas”.
It’s gonna suck, and be unmaintainable, and insecure, and fragile. But I bet it could do it and it’d work for a little while.
That’s not “working saas” tho.
Its like calling hello world a “production ready CLI application”.
What makes it “working”, is that the Software part of Software as a Service, is available as a Service.
The service doesn’t have to scale to a million users. It’s still a SaaS if it has one customer with like 4 users.
Is this a pedantic argument? Yes.
Are you starting a pedantic fight about the specific definition of SaaS? Also yes.My CGI script is a SaaS.
Kinda.
Ignoring the pedantic take that nearly every website is a saas.
And the slightly less pedantic take that every interactive website is a saasIf your website is an app that does a thing that a user wants, it’s a saas.
Your website just does mpeg to gif transcoding? That’s a saas. Online text editor? SaaS. Online tamagotchi? SaaS.If it doesn’t scale to the number of users who want or need to use it, then it’s not a very good SaaS. But SaaS it is.
Mmmmmmmmmmmmm no
We just built and deployed a fully functional AWS app for our team entirely written in AI. From the terraform, to the backing API, to the frontend Angular. All AI. I think AI is further along here than you suspect.
I’m skeptical. You are saying that your team has no hand in the provisioning and you deputized an AI with AWS keys and just let it run wild?
How? We try to adopt AI for dev work for years now and every time the next gen tool or model gets released it fails spectacularly at basic things. And that’s just the technical stuff, I still have no idea on how to tell it do implement our use cases as it simply does not understand the domain.
It is great at building things other have already built and it could train on but we don’t really have a use case for that.
My impression is that with some guidance it can put together a basic skeleton of complex stuff too. But you need a specialist level of knowledge to fix the fail at compile level mistakes or worse yet mistakes that compile but don’t at all achieve the intended result. To me it has been most useful at getting the correct arguments for argument heavy libraries like plotly, remembering how to do stuff in bash or learning something from scratch like 3js. Soon as you try to do something more complex than it can handle, it confidently starts cycling through the same couple of mistakes over and over. The key words it spews in those mistakes can sometimes be helpful to direct your search online though.
So it has the potential to be helpful to a programmer but it cant yet replace programmers as tech bros like to fantasize about.
Claude code can make something that works, but it’s kinda over engineered and really struggles to make an elegant solution that maximises code reuse - it’s the opposite of DRY.
I’m doing a personal project at the moment and used it for a few days, made good progress but it got to the point where it was just a spaghetti mess of jumbled code, and I deleted it and went back to implementing each component one at a time and then wiring them together manually.
My current workflow is basically never let them work on more than one file at a time, and build the app one component at a time, starting at the ground level and then working in, so for example:
Create base classes that things will extend, Then create an example data model class, iterate on that architecture A LOT until it’s really elegant.
Then Ive been getting it to write me a generator - not the actual code for models,
Then (level 3) we start with be UI.layer, so now we make a UI kit the app will use and reuse for different components
Then we make a UI component that will be used in a screen. I’m using flutter as an example so It would be a stateless component
We now write tests for the component
Now we do a screen, and I import each of the components.
It’s still very manual, but it’s getting better. You are still going to need a human cider, I think forever, but there are two big problems that aren’t being addressed because people are just putting their head in the sand and saying nah can’t do it, or the clown op in the post who thinks they can do it.
-
Because dogs be clownin, the public perception of programming as a career will be devalued “I’ll just make it myself!” Or like my rich engineer uncle said to me when I was doing websites professionally - a 13 year old can just make a website, why would I pay you so much to do it. THAT FUCKING SUCKS. But a similar attitude has existed from people “I’ll just hire Indians”. This is bullshit, but perception is important and it’s going to require you to justify yourself for a lot more work.
-
And this is the flip side good news. These skills you have developed - it’s is going to be SO MUCH FUCKING HARDER TO LEARN THEM. When you can just say “hey generate me an app that manages customers and follow ups” and something gets spat out, you aren’t going to investigate the grind required to work out basic shit. People will simply not get to the same level they are now.
That logic about how to scaffold and architect an app in a sensible way - USING AI TOOLS - is actually the new skillset. You need to know how to build the app, and then how to efficiently and effectively use the new tools to actually construct it. Then you need to be able to do code review for each change.
</rant>
-
idk ive seen some crazy complicated stuff woven together by people who cant code. I’ve got a friend who has no job and is trying to make a living off coding while, for 15+ years being totally unable to learn coding. Some of the things they make are surprisingly complex. Tho also, and the person mentioned here may do similarly, they don’t ONLY use ai. They use Github alot too. They make nearly nothing themself, but go thru github and basically combine large chunks of code others have made with ai generated code. Somehow they do it well enough to have done things with servers, cryptocurrency, etc… all the while not knowing any coding language.
That reminds me of this comic strip…
Might be satire, but I think some “products based on LLMs” (not LLMs alone) would be able to. There’s pretty impressive demos out there, but honestly haven’t tried them myself.
AI is yet another technology that enables morons to think they can cut out the middleman of programming staff, only to very quickly realise that we’re more than just monkeys with typewriters.
Well I think I am a monkey with a typewriter…
To be fair… If this guy would have hired a dev team, the same thing could happen.
True, any software can be vulnerable to attack.
but the difference is a technical team of software developers can mitigate an attack and patch it. This guy has no tech support than the AI that sold him the faulty code that likely assumed he did the proper hardening of his environment (which he did not).
Openly admitting you programmed anything with AI only is admitting you haven’t done the basic steps to protecting yourself or your customers.
But then they’d have a dev team who wrote the code and therefore knows how it works.
In this case, the hackers might understand the code better than the “author” because they’ve been working in it longer.
We’re monkeys with COMPUTERS!!!
Yeah! I have two typewriters!
i have a mobile touchscreen typewriter, but it isn’t very effective at writing code.
I was going to post a note about typewriters, allegedly from Tom Hanks, which I saw years and years ago; but I can’t find it.
Turns out there’s a lot of Tom Hanks typewriter content out there.
He donated his to my hs randomly, it was supposed to goto the valedictorian but the school kept it lmao, it was so funny because they showed everyone a video where he says not to keep the typewriter and its for a student
That’s … Pretty depressing.
But I thought vibe coding was good actually 😂
Vibe coding is a hilarious term for this too. As if it’s not just letting AI write your code.
“If you don’t have organic intelligence at home, store-bought is fine.” - leo (probably)
“Come try my software! I’m an idiot, so I didn’t write it and have no idea how it works, but you can pay for it.”
to
“🎵How could this happen to meeeeee🎵”
taste of his own medicine
Eat my SaaS
I hope this is satire 😭
The increasing use of AI is horrifying. Stop playing Frankenstein! Quit creating thinking beings and using them as slaves.
He should be promoted to management! Specifically head of cyber security! They also love security by obscurity and knowing nothing about what they are doing!
CIO, Peregrine Took.
