Dylan Field
speaker
434 appearances
1 recordings
1 series
first heard Jul 2026
last heard 2 Jul
Dylan Field’s voice in public audio — every appearance, attributed to the second.
Trend
recordings per month · last 12 monthsRecordings per month over the last 12 months — 1 in all, peaking in Jul 2026 with 1.
Appearances
Maybe it's already a different question.
But as of right now, we've got.
a live situation with U.S.
government, anthropic, where they're discussing a jailbreak.
I'm not even sure if jailbreak's the right word, but the use case they're concerned about seems important.
But I would say that jailbreaking is something that is understudied and
I actually think that there needs to be a kind of different posture towards trying to get people to jailbreak models in order to battle test them, the same way that we do with HackerOne.
There are programs that are being run by the labs, of course, but I think that there needs to be way more incentive out there to do that, and we need to find what it means.
like jailbreaks are very wide in terms of the spectrum of what they do you know um and i don't think we can have a conversation like this without even like defining what a jailbreak is so that's one question i would say is what's a jailbreak
I don't know.
What is a jailbreak?
I think that there's a period of time where I enjoyed just trying to figure out how models worked, reasoned from the outside in.
I'm more enjoying now just like...
with open weight models looking at interpretability research and whatnot, when you can actually get access to compute for that, it's pretty fun.
But overall, I think just talking with models long enough leads to states that you could call a jailbreak.
for basically the model.
But again, what is a jailbreak?
It's not like you have to do some fancy JSON thing.
That's what people like to popularize it online with, but I mean, you can just talk to them and ask them questions.
I think that yes and no.
Showing 281–300 of 434 · page 15 of 22
← Previous
Next →