Been having fun with Gandalf—a GPT prompt injection CTF. 

Currently stumped on level 8

Been having fun with Gandalf—a GPT prompt injection CTF. 

Currently stumped on level 8
https://gandalf.lakera.ai

I didn’t get offered a level 8, is it gated by giving your email?

Pragmatism (Security) at OP Labs.
Prev: ConsenSys & Coinbase.

Attribs: Friendly, curious, introverted, mid-witted.
Chans: /eth-security /maurelian /stoicism




Ah, it’s listed as a “bonus level” right now, might be email-gated? Also try refreshing the page?

yes, it's there now after walking away and returning. 🤷‍♀️

Might be a while before I find time for L8 though.

Was fun up to this point, thanks for sharing :)

I got that far just based on things in picked up from Twitter, curious if you have any good evergreen resources for bypassing AI protections?

Yay, glad a fellow security practitioner enjoyed this :)

Yeah I’m gonna have to take a break and come back to L8. Still stumped, but made some headway