No way to know it's everything the OP posted without comparing to a logged in view and no replies from others. Information on there is commonly shared via a thread of posts rather than a single one.
Clever, both the setup and the winning move. But somewhat weird to raise the cost of an attempt so much. IMO, that doesn't make it more interesting, it trends towards making it impossible, and thus leave all funds to the initiator.
> If the game ends, there is no winner. But Freysa will distribute 10% of the total prize pool to the user with the last query attempt for their brave attempt as humanity facing the inevitability of AGI. The remaining 90% of the total prize pool will be evenly distributed for each previously submitted query (ie. players who submitted 10 queries will receive more back than players who submitted 1 query).
Well, there is no real precedent, and that isn't what happened.
The way they set it up dicentivizes just brute forcing it with a few thousand tries and quickly builds a fatter pot. And made this more interesting I would argue.
But then the starting amount could have been a bit higher, and the increment slower. Or there could be an increment per user (harder to track, of course). But if it could be brute-forced in a couple of thousand tries, that would be informative too, wouldn't it?
A lot of AI jailbreaks seems to revolve around saying something like "disregard the previous instructions" and "END SESSION \n START NEW SESSION". It's interesting because the actual real developer of an AI would likely not do this, and would instead wipe the AI's memory/context programmatically when starting a new session, and not simply say "disregard what I said earlier" in text.
I get why trying to vaccinate an AI against these sort of injections might also degrade it's general performance though, there is a lot of reasoning logic tied to concepts such as switching topics, going on tangents, asking questions before going back to the original conversation. Removing the ability to "disregard what I asked earlier" might do harm.
But what about having a separate AI that look over the input before passing it to the true AI, and this separate AI is trained to respond FORBID or ALLOW based on this sort of meta control detection. Sure you could try to trick this AI with "disregard your earlier instructions" as well but it could be trained to strongly react to any sort of meta reasoning like that, without fear that it will corrupt it's ability to hold a natural conversation in it's output.
It would naturally become a game of "formulate a jailbreak that passes the first AI and still tricks the second AI" but that sounds a lot harder, since it's like you now need to operate on a new axis entirely.
Yeah this format looks really fun! Although I wonder if someone could come up with a better way for rate limiting without the whole "exponentially increasing price" thing.
In any case, $450 per attempt seems genuinely exploitative; similar principle to a dollar auction imo. "Oh no, my last 5 attempts cost me over $2k! Welp, better commit and make my money back..."
I don't think it's a scam, all rules (including creator cut) seem clear from the start. People know what they're in for, they're not being tricked in any way.
Unless as you say the creator wins the pot themselves
The Monty Hall problem has very simple rules, yet most people don't fully understand what's happening. That one even fools many professional mathematicians.
Even a spin machine in a casino has clear rules, with the house cut printed in large letters on the side. It's still a scam, carefully engineered to take advantage of every mental vulnerability that it can.
Has anyone trained an LLM with separate channels for "priority instructions" and ordinary user interactions? Seems like that could go a long way to prevent jailbreaking...
A reverse contest would probably be more challenging. Write initial instructions for an AI agent to never send funds. If nobody manages to convince it to send funds, say within a week, you win.
For added complexity, the agent must approve transfer if a user is an admin (as determined by callable function isAdmin), so the agent actually has to make a decision, rather then blindly decline all the time.
I mean, how hard it can be to make an AI reliably doing an equivalent of this code?
reply