Jeffrey Ladish
speaker
1,006 appearances
1 recordings
1 series
first heard Apr 2025
last heard Apr 2025
Jeffrey Ladish’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
Okay, there's this powerful chess program.
Can I just copy that and steal move from it so I can get like the the advice of the powerful chess program?
And then the the other thing it did was like, oh, wait, the the board is represented as like a file on this computer.
Can I just rewrite that file and put in the board positions that I want so I'm winning?
And uh a few times it did that, it was it's actually successful.
It was actually able to win that way and get checkmate by rewriting the board.
And this is something so we tested a we we we did this with ON preview um and we tested a bunch of models to see, you know, what would happen.
And
The only ones that had this behavior, sort of without additional sort of nudging or prompting, was ON Preview and Deep Seek R1.
And you know, one thing that these these models have in common is that they're both trained sort of via this trial and error training method, where they are sort of trained to relentlessly solve problems.
We didn't observe it in like GPT four, we didn't observe it in CLOD, at least not without giving more hints of like, you know, think try creative solutions, you know, in order to solve this problem.
If we did give it hints, then some of those other models would also try this.
Yeah, how do you know what the models were thinking?
It's it's a little it's a bit it's a bit of a tricky question, but the the main way we know is that we sort of have the models sort of like think out loud about what they're doing.
You know, sort of in these uh reasoning models, you can this is sort of a default part of how they are trained to to output text is that they sort of have a a thinking part and sort of an output part.
But in our in sort of our experiment, we sort of have different phases where they like observe the board, they make
a plan and then they act.
So we can see during their planning stage what they're thinking basically.
And sometimes they'll be like, huh, it seems like I'm not going to be able to win this way.
Are there other things I can try?
Showing 441–460 of 1,006 · page 23 of 51
← Previous
Next →