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
Sure, yeah.
Lots of exciting things have happened since then.
We've hired a few more people on both the evals team and the governance team, which I think is really cool, making most of there.
And then obviously the research progress has been just going on over time on evaluations.
We built a lot of new evaluations.
I also feel like we now have a much better
threat model and theory, like m a lot of theory progress on
What kind of e bills we should be building?
In what order?
How do we even build them properly?
Signs of e bills type uh progress.
And then a lot of interpretability progress as well, uh where we just have a a new interpretability.
method that we are currently exploring and really excited about.
And on the governance side, things have also moved been moving very, very fast with the EU AI office being built up, with the various AI safety institutes and also just a ton of things happening just all over the place where yeah, we have a lot of very exciting opportunities to speak to highly influential people and and answer their questions and be helpful and
Yeah, give just technical advice to the extent to which we can but yeah, overall it felt quite a wild ride, but in a very positive sense.
Yeah, sure.
First of all, it's still our big focus.
So scheming, deceptive alignment, deception, these are the kind of things that we're really worried about.
And why I I I think really the intuition is like, as long as your model is not deceptive and it is misaligned or bad, you can just ask it, right?
You can just be like, Hey, are you bad?
Showing 1–20 of 481 · page 1 of 25
Next →