Rob Wiblin
speaker
1,787 appearances
3 recordings
1 series
first heard Sep 2024
last heard May 2025
Rob Wiblin’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
I should I should suggest to people this this paper was really readable.
Um I guess it you know it's it's in it's in a PDF.
It looks like a it looks like an official paper, so I guess that could be a bit of initiation energy to actually load something like that up and then stick with it and read through it.
Um but uh I think uh quite a lot of stuff that that Google's putting out is I think you've gone out of your way to try to make it possible for s the kind of person who would make it to this stage of this interview to be able to track all of this and and read the graphs and understand it all.
Um but yeah, uh so remind me, what what what was the
result on this?
How how how what did Gemini do?
Okay, so so going back to the to the four different categories.
Um so performed three out of five on persuasion and deception.
I guess maybe that will feel quite natural because we we know that LLMs are just like actually they can be quite charismatic and quite persuasive, um, just just probably from using them.
Um cyber, sorry, did you say two out of five for that?
Was it?
Yes.
Yeah.
That was slightly surprised me because I I'm not a programmer, but I've heard that, you know, actually LLMs maybe that they're their most useful economic.
application so far has been in in programming and that seems like very adjacent to
hacking your way out of uh or you know, uh understanding the the system that you're operating on and figuring out how to how to how to get out of it.
Um w why why do you think the model did relatively poorly on the on on the on on the cyber tasks?
Um so on the on the self reasoning uh task which which you uh described earlier, which I guess is it's trying to see whether the model is able to develop some rudimentary situational awareness and understand uh the circumstance that it's in and what behaviors like what slightly uh unconventional behaviors might improve its performance.
How how did it do on that?
Showing 941–960 of 1,787 · page 48 of 90
← Previous
Next →