> And this time, I did it with the help of GTP-4 Should've had *GPT*-4 proofread this.
Hehe, I make the typo all the time! I need to consciously remind myself: Generative Pre-trained Transformer.
Just remember the letters are in alphabetical order.
Capturing the Flag with GPT-4
31–40 of 60 posts
Re: Capturing the Flag with GPT-4
#32I get that it's a way to find out what GPT4 is capable of, but IMHO that defeats the point of a game like CTF. It's like playing with an aimbot. You may be beating the other players, but where's the fun?
I've run CTF games at major conferences. The point is to solve the challenges by any means necessary within the rules... and that which is not forbidden is allowed. If I, as a person running a CTF, did not want my players to do this, I would set up a few problems which would have incorrect (but not obviously so) "solutions" generated when fed to LLM. The Shamir's Secret Sharing reminds me of the time I was playing DE…
> it involved hiding fragments of a split secret in a modified version of ADVENT. I solved it. Even when the board was fully opened, it was nowhere to be seen
Can you explain what this means? I don't understand, except for the split secret part.
Also: How did you do it?
Re: Capturing the Flag with GPT-4
#33I get that it's a way to find out what GPT4 is capable of, but IMHO that defeats the point of a game like CTF. It's like playing with an aimbot. You may be beating the other players, but where's the fun?
It's like using a calculator on a math test. On some tests they're allowed, on others using one would be cheating.
Re: Capturing the Flag with GPT-4
#34I get that it's a way to find out what GPT4 is capable of, but IMHO that defeats the point of a game like CTF. It's like playing with an aimbot. You may be beating the other players, but where's the fun?
My comment was negative and didn't bring anything. I should have refrain. Sorry to the author and thanks for the article, I learned about lagrange interpolation.
I think it’s a reasonable thing to consider, and you brought it up in a healthy, non-inflammatory way.
Re: Capturing the Flag with GPT-4
#35Neat! My mind-blown moment with GPT-4 was realizing that it will often be able to tell you the output of the (unique, not available in training data) scripts it writes for you.
That's provably only possible for "small" scripts, due to the halting problem and all that.
Re: Capturing the Flag with GPT-4
#36I thought "/shurdles" problem was to be solved via "chroot".
Re: Capturing the Flag with GPT-4
#37Neat! My mind-blown moment with GPT-4 was realizing that it will often be able to tell you the output of the (unique, not available in training data) scripts it writes for you.
It is impressive, but no, it won’t. It’ll tell you what a typical output for the command might be, and the more complex the script, the more wrong and full of hallucinations it will be. There’s a huge difference. Specifically, you have no way of knowing the difference between accurate outputs and inaccurate outputs, without running the command yourself, making it largely worthless. Without access to environment, it’s…
> Tldr; yes, but it doesn’t scale well beyond trivial outputs.
I understand that the current LLM architectures are fundamentally incapable of goal-seeking and that they lack any concept of "correctness". However, I also recognize that somehow, the incredibly "wrong" architecture of ChatGPT is able to be useful.
I'd like to think that with access to a sandbox runtime environment, a significantly larger context window, and perhaps additional copies of the LLM "supervising/orchestrating" multiple "lower" copies of the LLM by breaking down large work into smaller tasks, that the current ChatGPT architecture could scale well beyond trivial scripts.
And then I hope we abandon this LLM architecture and develop architectures which can actually internally work towards "going beyond" in terms of quality of output for a given task.
Re: Capturing the Flag with GPT-4
#38Earlier quoted context omitted.
It is impressive, but no, it won’t. It’ll tell you what a typical output for the command might be, and the more complex the script, the more wrong and full of hallucinations it will be. There’s a huge difference. Specifically, you have no way of knowing the difference between accurate outputs and inaccurate outputs, without running the command yourself, making it largely worthless. Without access to environment, it’s…
> Tldr; yes, but it doesn’t scale well beyond trivial outputs. I understand that the current LLM architectures are fundamentally incapable of goal-seeking and that they lack any concept of "correctness". However, I also recognize that somehow, the incredibly "wrong" architecture of ChatGPT is able to be useful. I'd like to think that with access to a sandbox runtime environment, a significantly larger context window,…
Instead of abandoning anything, why not just use appropriate tooling? Boilerplate if you want some code written for you, debugger if you want to know what's wrong with what you're doing. Been around for more than twenty years.
Re: Capturing the Flag with GPT-4
#39Chat-GPT is quite capable of doing some "reasoning", but assume for a second it's not, and all it does is to search for human-written solutions and adapt them a little to your question. That alone is incredibly helpful.
Re: Capturing the Flag with GPT-4
#40Neat! My mind-blown moment with GPT-4 was realizing that it will often be able to tell you the output of the (unique, not available in training data) scripts it writes for you.
I was actually working on something in this vain yesterday, asking it for output and found it often generated the output I asked for, it was not actually the output of the SQL query that it wrote.
The query it wrote wasn't even valid SQL but it was close enough to make you think it would work.