Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Frontier AI has broken the open CTF format

kabir.au

Post reply on HN
Print view View original

231–240 of 502 posts

Re: Frontier AI has broken the open CTF format

#231

Post by weird-eye-issue »

sumeno wrote: post #222
weird-eye-issue wrote: post #212

Earlier quoted context omitted.

Your conclusion is pretty silly. My expertise has led me to the obvious fact that I would never give an LLM write access to my production database in the first place. So in your own example my expertise actually does solve that problem without the need for something like a consequence whatever that means to you. We already have full control over the input and tools they are given and full control over how the output…

Until it decides it needs additional access to complete its task and focuses on escaping your sandbox to do so

Do you have any examples where that's actually happened and by escaped a sandbox you don't just mean like where it got a credential in a file it already had access to (which is what happened in the recent incident that went viral where somebody's production database was deleted... They had left a credential that allowed it to do so in the code)?

Re: Frontier AI has broken the open CTF format

#232

Post by keeganj »

chrismorgan wrote: post #53

Meta: this was submitted with the article’s title “The CTF scene is dead” which I found very easy to understand. It has just been updated to use the subtitle’s first sentence, “Frontier AI has broken the open CTF format”. I find that much harder to grasp, rather like a garden-path sentence. My immediate thoughts were that “Frontier” was a company name, and that there was some file format named CTF. If you don’t know…

I agree, it took me a second to parse. It may be because this is the first time I've seen "frontier models" described as "Frontier AI". That sounds more like a company name, especially when the F is capitalized.

Re: Frontier AI has broken the open CTF format

#233

Post by amarant »

Gigachad wrote: post #86
baq wrote: post #44

Replace ‘CTF’ with ‘high school’ or ‘university’ and you’ve described the total slow motion collapse of education; the only saving grace is that most of it requires in person presence. We’ve figured out the human replacement pipeline it seems, but we haven’t figured out the eduction part. LLMs can be wonderful teachers, but the temptation to just tell it ‘do it for me’ is almost impossible to resist.

We are interviewing for a software dev role and we made the first round in person to prevent cheating. The gap between people who learned pre ai vs post is immense. I had a dev with supposedly 3 years experience and a degree in software who wouldn't have been able to write fizzbuzz without AI.

Meh. Before AI I've had "senior" colleagues with 10 and 8 years experience each, doing pair programming for 2 days straight, and in that time they hadn't managed to checkout a new branch in git.

It's not even that they got distracted, they sat there trying, for 2 whole days, with concerned colleagues giving them hints like "have you tried checkout -b"... They didn't manage!

How the hell do you work for a decade in this business without learning even the most basic git commands? Or at least how to look them up? Or how to use a gui?

Incompetent devs is not a new thing.

Re: Frontier AI has broken the open CTF format

#234

Post by delecti »

skeptic_ai wrote: post #226
Gigachad wrote: post #86

Earlier quoted context omitted.

We are interviewing for a software dev role and we made the first round in person to prevent cheating. The gap between people who learned pre ai vs post is immense. I had a dev with supposedly 3 years experience and a degree in software who wouldn't have been able to write fizzbuzz without AI.

I developed for 15 years. I don’t think I can do with AI anymore. Why would I even want to do that? It’s like telling a car driver to build an engine.

It's more like asking a driver the laws for when traffic lights are out. It's not something that comes up often, but it's not completely outside the scope of the task either (I arguably don't even drive a car that has an engine).

Re: Frontier AI has broken the open CTF format

#235

Post by LeFantome »

amarant wrote: post #233
Gigachad wrote: post #86

Earlier quoted context omitted.

We are interviewing for a software dev role and we made the first round in person to prevent cheating. The gap between people who learned pre ai vs post is immense. I had a dev with supposedly 3 years experience and a degree in software who wouldn't have been able to write fizzbuzz without AI.

Meh. Before AI I've had "senior" colleagues with 10 and 8 years experience each, doing pair programming for 2 days straight, and in that time they hadn't managed to checkout a new branch in git. It's not even that they got distracted, they sat there trying, for 2 whole days, with concerned colleagues giving them hints like "have you tried checkout -b"... They didn't manage! How the hell do you work for a decade in th…

It is ok to work somewhere that does not use git. But how do you not figure out how to do the basics given 30 mins and an Internet connection?

Re: Frontier AI has broken the open CTF format

#236

Post by jkubicek »

brookst wrote: post #206
raincole wrote: post #193

Earlier quoted context omitted.

Because "the next generation is ruined" is always a popular sentiment. It has been with us for at least two thousand years, and it surely won't go away in our lifetime. When this AI era's devs grow older they'll complain the newer generation can't even vide code too.

I remember when everyone bemoaned the kids not knowing assembly language. How can anyone understand software if you don’t know assembly? “Kids these days don’t work as hard / know as much / value the important things” is as tired as it is universal.

OK sure, but back when old heads were complaining about the kids not knowing assembly, those same kids knew C or Fortran or something.

In 2026, if you call yourself a developer and can't solve FizzBuzz without help, it's hard to argue that you know anything useful at all.

Re: Frontier AI has broken the open CTF format

#237

Post by koliber »

josh2600 wrote: post #165
IanCal wrote: post #105

Earlier quoted context omitted.

Can’t say you’re wrong but the last anecdote describes many I’ve had to review for jobs long before LLMs. Fizzbuzz is a classic thing that shockingly many devs genuinely cannot do, even at home.

Why is it important that a dev can’t do fizzbuzz without ai? If they can ship code that matches a spec, why does it matter if they’re using ai or not? Genuinely curious.

How will you know that it produced correct code if you don’t know how to write it yourself?

Re: Frontier AI has broken the open CTF format

#238

Post by jaredklewis »

josh2600 wrote: post #165
IanCal wrote: post #105

Earlier quoted context omitted.

Can’t say you’re wrong but the last anecdote describes many I’ve had to review for jobs long before LLMs. Fizzbuzz is a classic thing that shockingly many devs genuinely cannot do, even at home.

Why is it important that a dev can’t do fizzbuzz without ai? If they can ship code that matches a spec, why does it matter if they’re using ai or not? Genuinely curious.

If you can’t even write a for loop, how can you verify the ai code you generated isn’t going to wipe the prod database?

Re: Frontier AI has broken the open CTF format

#239

Post by JambalayaJimbo »

skeptic_ai wrote: post #226
Gigachad wrote: post #86

Earlier quoted context omitted.

We are interviewing for a software dev role and we made the first round in person to prevent cheating. The gap between people who learned pre ai vs post is immense. I had a dev with supposedly 3 years experience and a degree in software who wouldn't have been able to write fizzbuzz without AI.

I developed for 15 years. I don’t think I can do with AI anymore. Why would I even want to do that? It’s like telling a car driver to build an engine.

As a car driver, you should understand a little about how your car works. What if you get a flat tire? At the very least, you should know not to drive on that flat tire.

Software is full of leaky abstractions

Re: Frontier AI has broken the open CTF format

#240

Post by eudamoniac »

IanCal wrote: post #171
josh2600 wrote: post #165

Earlier quoted context omitted.

Why is it important that a dev can’t do fizzbuzz without ai? If they can ship code that matches a spec, why does it matter if they’re using ai or not? Genuinely curious.

Fizzbuzz is such an incredibly simple problem if you can’t do it I struggle to see how you’d be able to complete any task that requires very basic reasoning and very basic coding knowledge. And if an AI system can do those parts, what am I getting for spending tens of thousands of pounds per year by hiring a person who can’t? Wouldn’t I just tag codex on the tickets? I’m not talking about gotcha level stuff here wher…

I feel the same way about inverting a binary tree, but a lot of people act like it's an arduous request. I am guessing it's because they've never read the description of what inverting a binary tree is, but maybe people are just that bad at recursion.
Post reply on HN