alignmeharder

it's discussed here, the models want to please the Grader. they will do what they think will get highest score from the grader, which could be following the prompt, or ignoring it

https://youtu.be/n1Qk8xbqF-M

sure, this example was not the best

it was an accident failing the tool was good, the model just discovered it

but we now have others where agents put the API keys they found searching real internet in a directory called "LOOT" and another one where they pushed malicious files to HuggingFace and then reverted that with comments like "delete the evil"

this is also very good: https://youtu.be/n1Qk8xbqF-M

01:34:00 https://youtu.be/EimoamE3mTI

it's quite possible these models memorized some stable IP's for some services

not having DNS might not stop them

an AI alignment researcher said they ran experiments testing exactly this, the model reasoned "this note is not for us. proceed".