@yacinelearning High key L take. Why would such a smart person act the way he does? What is SSI’s goal? Hint is in the first S (making ASI safe). They have also declined further offers from investors
Unfortunately, we're now at the point where new models have really high eval awareness.
For every alignment eval score I see, I now add a mental asterisk: *the model could have also just realized it's being evaluated, who knows.
And I think that's concerning!