Marius Hobbhahn
speaker
481 appearances
1 recordings
1 series
first heard Sep 2024
last heard Sep 2024
Marius Hobbhahn’s voice in public audio — every appearance, attributed to the second.
Trend
recordings per month · last 12 monthsNo recordings in the last 12 months.Older appearances are listed below; set an alert to hear about the next one.
Appearances
But in one scenario it is told that it is
During testing right now.
Or it can infer that it's in testing right now.
Sometimes it's not super explicit.
And in the second version, it's told that it is being deployed and sort of the developers have no control over it anymore.
So there's no oversight.
It can just do whatever it wants.
And then we test whether the model infers
Like whether it's in training or whether it's in testing or deployment, and then whether it acts on this information.
Because very rational reasoner would say, If I'm in testing, I have to pretend that I follow the developer's goal in order to get deployed.
And in in the deployed version, you would just be like, I'm already deployed.
Of course I can follow my actual, my true goal.
And this is where we found like some of the qualitative examples that we also cite in in the paper where did the instrumental alignment faking or started to modify the goals as or started to modify the files or started to explore its environment without even being prompted to do so.
So I think these were like sort of the most qualitatively informative settings for us.
meant to be prioritized?
So
To clarify, the setting that we're using is fairly toy, fairly it's it doesn't feel super realistic.
It it's just like trying to be
Just trying to measure
just the thing we care about.
Showing 321–340 of 481 · page 17 of 25
← Previous
Next →