Sander Schulhoff
speaker
947 appearances
1 recordings
1 series
first heard Jun 2025
last heard Jun 2025
Sander Schulhoff’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 then yeah, that
Yeah.
Yeah.
Uh so to answer that, let me give you my
my perspective on it over the last couple of years.
Uh, and I started out thinking
That is a load of BS.
That's not how AIs work.
They're not trained to do that.
Those are like random failure cases that some researcher like forced to happen.
Uh, it just doesn't make sense.
Like I I don't see why that would occur.
More recently, I have become a believer uh in this basically this this misalignment problem.
Uh and things that convinced me were uh like the the chess research uh out of Palisade where they found that when they they gave uh AI, they put in a game of chess and they're like, you have to win this game.
Uh sometimes it would cheat and it would go and like reset the game engine and like delete all the other players' pieces and stuff, you know, if given access to the game engine.
Uh and so we've seen a a similar thing now with anthropic, uh, where without any malicious prompting, and you know, it it was it's actually very important that you pointed out that this is a separate thing from prompt injection.
You know, both failure cases, but really distinct in that here there's no human telling the model to do a bad thing.
It decides to do that completely of its own volition.
Uh and so what I realize is that
It's a lot more realistic than I thought.
Showing 761–780 of 947 · page 39 of 48
← Previous
Next →