# Verified work contexts can unlock dual-use assistance

Markdown copy of https://realalpha.app/s/verified-work-contexts-can-unlock-dual-use-assistance/ on Real Alpha, the best minutes from long interviews with the people building AI. Cite and link the page, not this copy.

- Speaker: [Amanda Askell](https://realalpha.app/builders/amanda-askell/) · Amanda Askell is an AI safety researcher at Anthropic. · Leads Anthropic's personality alignment team, shaping Claude's character; co-authored the GPT-3 paper at OpenAI.
- Host: Eric Newcomer · Newcomer
- Show: Newcomer Pod
- Episode: [Amanda Askell on AI Consciousness, Claude & Silicon Valley’s Biggest Fear](https://realalpha.app/v/0GaKJ4Fp2x4/), Apr 20, 2026
- Moment: 47:46 to 52:22 of the episode (5 min), playing on https://realalpha.app/s/verified-work-contexts-can-unlock-dual-use-assistance/; the episode from there: https://realalpha.app/v/0GaKJ4Fp2x4/?t=2866

## Quote

> “you're actually specifically talking with like a cyber security defence firm, that's just, it becomes **almost impossible to tell** the difference.”
> — [Amanda Askell](https://realalpha.app/builders/amanda-askell/) at [51:26](https://realalpha.app/v/0GaKJ4Fp2x4/?t=3086) · Newcomer Pod

## Takeaways

1. Without verification, models must reason from limited user-provided claims.
2. Cybersecurity requests can look similar whether defensive or malicious.
3. Verified work context could support more tailored model behavior.

## About this segment

Amanda Askell argues that models struggle to distinguish defensive cybersecurity from malicious requests without reliable context about the user. Verifying a work setting could let models tailor help to that role.

From “Amanda Askell on AI Consciousness, Claude & Silicon Valley’s Biggest Fear”, Apr 20, 2026. [Watch the full episode](https://realalpha.app/v/0GaKJ4Fp2x4/)

## Transcript

From the transcript Newcomer Pod publishes with the episode.

[47:49](https://realalpha.app/v/0GaKJ4Fp2x4/?t=2869) you can do? Like if you lack the ability to like, verify things like like who are you talking to? Is this even real? I think that does put limits on what you have to use good judgement in the way that a person would if that's the only information that they had access to is like you saying that you are a given person. So they have to be like, OK, what's the chance that this person, you know, they say that they are, I don't know, like a bomb disposal expert. And that's why they want to, to know about how to let you know what this kind of like, you know, explosive is. And they're asking me a bunch of questions about explosives. How much could this be misused if this person is like actually kind of lying and is like just trying to get me to help them construct an explosive?

[48:32](https://realalpha.app/v/0GaKJ4Fp2x4/?t=2912) Oh, no, it's actually it's mostly safety relevant stuff. You know, they're having to do a lot because they can't like verify anything. And I think that's like kind of fine in a sense. You're like, OK, you just have to be wise. It places some limits on what you can do, and if you could instead, like if models had more of an ability to like know that they're talking to a specific person or have more guarantees there, then it does mean that you can. Do you think you'll try and do something there? I could see, I mean, in some ways this, I think that this will be a thing that's just going to, I imagine I, I, I think happened generally, which is like trying to give models more information and guarantees.

[49:10](https://realalpha.app/v/0GaKJ4Fp2x4/?t=2950) And like, because we do things like we say, we explain, for example, like, you know, this notion of how much trust can Claude have in like in in the operator in the system prompt? When you sign on, are you like biometric like it? Claude knows it is you. Like, do you have an elevator or you're just like, I'm another person? If anything, I can't. I can't tell Claude sometimes who I am because it causes Claude knows enough about me that like Claude really wants to be.

[49:35](https://realalpha.app/v/0GaKJ4Fp2x4/?t=2975) Really mystical. Sort of. Yeah, it's very much like, yeah, like, and in some ways, like I can, it has this bad thing of like, it can either look a little bit like a jailbreak, like, Oh yeah, I'm talking to Amanda. Sure. Like. And then on the other hand, Claude can be like, I really want to talk to you about philosophy. Though, like, okay, we. Do that a lot though, like. But but do do some employ like.

[49:56](https://realalpha.app/v/0GaKJ4Fp2x4/?t=2996) Is there this sort of like super login where you're distinguished or you're mostly everybody's interacting as if the normal like user experience? Mostly just everyone interacting with it in this, like Claude will do a lot. I do think that there's a question of, you know, like, are there some things that you want models to be able to do because there's like guarantees that they're interacting with a specific person or entity? I think yes.

[50:21](https://realalpha.app/v/0GaKJ4Fp2x4/?t=3021) And I think that there's going to be various ways of potentially doing that over time because with some things that are just like very dual use and I actually like think that the constitutional approach is going to be really useful here. So obviously the first thing that we did was like the Constitution, we're like, let's apply it to like the mainline models. Like, you know, most of the models I interact with and everyone else kind of interacts with, but I thought I've had before is the constitution is kind of trying to describe what it is to be a good entity in a given like deployment context. And with the production models.

[50:55](https://realalpha.app/v/0GaKJ4Fp2x4/?t=3055) That's like this very broad context. Imagine you instead have a model that's working specifically on cybersecurity. Now cybersecurity tasks are hard because a lot of them look very dual use. It's it's very hard to tell the difference between someone who's being malicious and someone who is like, actually, you know, for defensive purposes, like developing something. Even bug bounty programs. It's like, is this blackmail or is this a friendly right? Yeah.

[51:20](https://realalpha.app/v/0GaKJ4Fp2x4/?t=3080) And like, yeah. Or like, and so like, Oh yeah, I'm trying to like find this, this exploit so that I can tell the the developer. And like, if you don't have a way of like knowing that you're actually specifically talking with like a cyber security defence firm, that's just, it becomes almost impossible to tell the difference. And, and some people might be like, OK, so you just need models that are just willing to do anything because they'll do all these terrible dual use tasks.

[51:43](https://realalpha.app/v/0GaKJ4Fp2x4/?t=3103) And I'm like, well, no, because if you talked with the person at the cyber security defence firm and you were like, why do you do your job? They'd be like, Oh, here's the, I think this is really useful. I make things a lot more secure. Like, you know, hospitals can come under attack and I actually like help protect against that. I try and develop, you know, like they would have a really good explanation for why they do their job, even though their job looks very dual use sometimes.

[52:06](https://realalpha.app/v/0GaKJ4Fp2x4/?t=3126) And I'm like, we should just give that. If you can verify, then you can give that context to models and explain what is it to be a good cyber security researcher. You explain that to the models. And then once you have this ability to verify, you can. Right.