“there's not really much point and it might be sort of a waste of time or perhaps even counterproductive to try to get the safety measures to be super robust relative to capabilities that don't exist yet”

ConceptSafety & governance

“They want the AI safety hub at the Tsinghua University College of AI to join that upper echelon. And it seems like the resources are there.”

ConceptSafety & governance

“those can be made available through a more structured program with know your customer and various other safeguards”

ConceptSafety & governance

“Yes. And it is conceivable that this process is accelerating over time, especially like everyone is now talking about continual learning, you know, because right now at least we have a centralized Right? So we have red teaming, we have frontier companies building these models,...”

ConceptSafety & governance

“Mythos is the first one where it seems to have insane power to do unexpected things. And like, do you think basically that we're pretty close to the limit here? Like, you know, because at first I thought, yeah, it was bad. It was safety washing, you know, they shouldn't have s...”

ConceptSafety & governance

“Now, we essentially started by looking at this method in like a neutral coding style setting. And we also wanted to apply this to a more alignment-relevant context. And so this is where we chose the feature honesty versus task completion. So this is task completion at all cost...”

ConceptSafety & governance

“I think there's an argument that actually maybe too much attention is paid to universal jailbreaks because in principle, a very targeted jailbreak could cause a lot of harm.”

ConceptSafety & governance

“Than these other categories. So that suggests to me that this is less about know-how or ability to these safeguards in place and more about, I'm not sure exactly what, like, I, I can't imagine that there's like that much revenue coming from like chemical things that would be s...”

ConceptSafety & governance

“I think we need to be a little bit more careful when it comes to things like bio and some of these other harm domains where sometimes knowing what the dangerous thing is, is half the battle”

ConceptSafety & governance

“Well, and I think the thing here is not, we're not saying don't use guardrails. The runtime governance of agents is hugely important. And I think—”

ConceptSafety & governance

“maybe time for a little thoughtful consideration of risk mitigation going forward”

ConceptSafety & governance

“Much of the AI safety discourse presumes that we're just going to sleepwalk into disaster. And my feeling was that that was never realistic.”

ConceptSafety & governance

“they were supposed to be, uh, testing these things and super secure air-gapped Faraday cages because they know what's best”

ConceptSafety & governance