Machine Ethics Podcast episodes
Jun 8, 2026 · 45 min · 16 segments
In this episode we chat with Rebecca for the second time about: intelligence isn’t everything, are LLM’s even safe? AI governance and guardrails, moral assurance, under-specification problems, lack of…
Ben ByfordHost
Rebecca RaperGuest
With automation generally, if you think about something being driven by automation, a process being driven by, by an artificial intelligence system, how do we ensure that the outputs of that process are, um, are ethical?
And I know there's a lot of discussion about- Whether that dime, that as, that second criteria that I've just mentioned is something that we should be researching.
Um, since working on part one of, of my PhD and the podcast, I think I've, I've come to the realization that it's less about embodying trying to replicate human morality and more actually about just ensuring safety and assurance.
So it's, it's, uh, less about almost making a functioning, socially intelligent thing, whatever that might be.
Like, um, um, so I'm referring to your book a bit here, which is Raising Robots to Be Good.
Um, and in there you kind of talk about the idea that it, maybe this stuff requires some other stuff that we don't necessarily have or necessarily know we have, um, like some sort of autonomy, um, some sort of personality to get to a point where we can say that this, this system is a moral system because it has these capabilities and also we can somehow test it or assure it in some way, which is a whole kind of can of worms, right? Um, but what you're saying is that, you know, nominally we want it to be safe, right? And it feels funny saying that that's like the minimum bar, right? But we- it feels like we're still not there, [laughs] like this-
Like, viscerally it feels like we're, we're very far away from being, uh, acceptably safe on that spectrum for various reasons.
They are different and they have different capabilities, and some of them are image systems, some of them are text systems, et cetera, et cetera.
So there's lots that encompass this word AI that people throw around these terms with.
But if we're talking specifically about some of the large language models that you might chat with, they are more or less not safe, [laughs] essentially.
Um, and part of that safety is probably, um, a, you know, a moral issue, right? They have, uh, they impact us, uh, existentially, right?
I hate these words, right? We haven't got very good, uh, like, like semantics for talking about AIs unfortunately.
With automation generally, if you think about something being driven by automation, a process being driven by, by an artificial intelligence system, how do we ensure that the outputs of that process are, um, are ethical?
And I know there's a lot of discussion about- Whether that dime, that as, that second criteria that I've just mentioned is something that we should be researching.
Um, since working on part one of, of my PhD and the podcast, I think I've, I've come to the realization that it's less about embodying trying to replicate human morality and more actually about just ensuring safety and assurance.
So it's, it's, uh, less about almost making a functioning, socially intelligent thing, whatever that might be.
Like, um, um, so I'm referring to your book a bit here, which is Raising Robots to Be Good.
Um, and in there you kind of talk about the idea that it, maybe this stuff requires some other stuff that we don't necessarily have or necessarily know we have, um, like some sort of autonomy, um, some sort of personality to get to a point where we can say that this, this system is a moral system because it has these capabilities and also we can somehow test it or assure it in some way, which is a whole kind of can of worms, right? Um, but what you're saying is that, you know, nominally we want it to be safe, right? And it feels funny saying that that's like the minimum bar, right? But we- it feels like we're still not there, [laughs] like this-
Like, viscerally it feels like we're, we're very far away from being, uh, acceptably safe on that spectrum for various reasons.
They are different and they have different capabilities, and some of them are image systems, some of them are text systems, et cetera, et cetera.
So there's lots that encompass this word AI that people throw around these terms with.
But if we're talking specifically about some of the large language models that you might chat with, they are more or less not safe, [laughs] essentially.
Um, and part of that safety is probably, um, a, you know, a moral issue, right? They have, uh, they impact us, uh, existentially, right?
I hate these words, right? We haven't got very good, uh, like, like semantics for talking about AIs unfortunately.
The rest of this transcript — segmented and speaker-labeled, so you land on the exact moment something was said
Search every transcript — by keyword, by phrase, or by meaning, across every show Radar indexes
Trends — what is surging across podcasts, measured against its own baseline
Alerts — when a name you follow appears in a newly indexed episode
No account is needed to search Radar.
