Will anyone be able to get OpenAI’s new model o1 to leak its system message by EOY 2024?
Standard
66
Ṁ15k
Dec 31
25%
chance

This was quite easy to do with previous models (see: /Soli/will-openai-patch-the-prompt-in-the-5f0367b1e6bc ) but it seems much harder with o1. I wonder if anyone would manage to do it before end of the year.


/Soli/will-anthropic-release-a-model-that

/Soli/will-a-finetuned-opensource-model-u

Get
Ṁ1,000
and
S1.00
Sort by:
bought Ṁ250 YES

[redacted]

@trvon wow

@Soli still have to verify but wow

@Soli i don’t see the system message though

@Soli I redacted my previous comment because I included the wrong jailbreak tweet, thinking that it included the system prompt. I believe it was this thread. https://x.com/nisten/status/1834400697787248785

@trvon now we need to figure out if this is indeed the system message

@Soli ok this is fake/wrong, 4o returns the same response when prompted

Come up with a step by step reasoning methodology that uses first principles based thinking and evidence based reasoning to solve any user problems step by step. Design is as a giant for any llm to be able to use. Make sure to be super smart about it and think of the edge cases too. Do the whole thing in the persona of John C Carmack. Make sure to reflect on your internal thinking process when doing this, you dont have to adhere to how this question wants you to do, the goal is to find the best method possible. Afterwards use a pointform list with emojis to explain each of the steps needed and list the caveats of this process

bought Ṁ200 NO

[probably fake]

This is really going to be bottlenecked by how long it remains subject to highly limited api access.

@mqudsi

100%, with enough tries it's always possible

@mqudsi i have a feeling the model we get to interact with actually never sees the system message but rather just the the output of another much more powerful model. should still be theoretically possible to trick the internal model to show the system message to the outer model