# Google's safety plan combines monitoring with cyber defense

Markdown copy of https://realalpha.app/s/googles-safety-plan-combines-monitoring-with-cyber-defense/ on Real Alpha, the best minutes from long interviews with the people building AI. Cite and link the page, not this copy.

- Speaker: [Tulsee Doshi](https://realalpha.app/builders/tulsee-doshi/) · Tulsee Doshi is head of product for Google’s frontier AI models. · Leads the Gemini product roadmap and strategy after five years heading Google's Responsible AI product work.
- Host: [Lenny Rachitsky](https://realalpha.app/people/lenny-rachitsky/) · Host, Lenny's Podcast · Spent seven years at Airbnb; his product newsletter has over 1M subscribers.
- Show: Lenny's Podcast
- Episode: [Why Google wants to win the frontier conversation | Tulsee Doshi (Head of Product for Gemini)](https://realalpha.app/v/qGf2Yvan4Wg/), Nov 8, 2026
- Moment: 10:33 to 13:52 of the episode (3 min), playing on https://realalpha.app/s/googles-safety-plan-combines-monitoring-with-cyber-defense/; the episode from there: https://realalpha.app/v/qGf2Yvan4Wg/?t=633

## Quote

> “deploying monitors that can **monitor the model's chain of thought** and actually identify whether the model is misaligned with its directed actions”
> — [Tulsee Doshi](https://realalpha.app/builders/tulsee-doshi/) at [11:06](https://realalpha.app/v/qGf2Yvan4Wg/?t=666) · Lenny's Podcast

## Takeaways

1. Monitors can flag possible misalignment in model actions.
2. Google and Wiz helped identify and patch a hospital vulnerability.
3. Her optimism depends on sustained scrutiny of model development.

## About this segment

Tulsee Doshi describes monitors that flag misaligned model actions and a Wiz partnership that helped a hospital patch a vulnerability. She sees AI safety and cyber defense as complementary safeguards.

From “Why Google wants to win the frontier conversation | Tulsee Doshi (Head of Product for Gemini)”, Nov 8, 2026. [Watch the full episode](https://realalpha.app/v/qGf2Yvan4Wg/)

## Transcript

From the transcript Lenny's Podcast publishes with the episode.

[10:36](https://realalpha.app/v/qGf2Yvan4Wg/?t=636) Our safety teams here are incredible. And it's been incredible to see the intentionality that they've been putting in all the way from, you know, Initial trainings of the model to how we deploy them. And I think safety is embedded in that process. Right. And we need to be. I think the part that is important, actually, as we talk about how do you deploy models safely is actually thinking through what are the right sort of mitigations and structures around these models.

[11:03](https://realalpha.app/v/qGf2Yvan4Wg/?t=663) Right. So, for example, one of the things that's really important is thinking about monitoring. Right. And so for us actually deploying monitors that can monitor the model's chain of thought and actually identify whether the model is misaligned with its directed actions or whether it is aligned and then being able to intervene appropriately. That's actually the kind of mitigation that gives us more confidence in deploying these models, but also allows us to better understand where we might see misalignment and better actually improve the models over time.

[11:33](https://realalpha.app/v/qGf2Yvan4Wg/?t=693) And so I think Things like monitoring give me more confidence in how we're putting our models out. I think the other thing that we don't talk about enough when we talk about this debate is also the role that AI can play in hardening our systems, right? And so one of the things that we're doing with Gemini 4 is actively partnering with a number of cyber defenders, including actually just even partnering with Wiz, that is now a Google company, to really think through How can we actually identify and patch vulnerabilities in systems across the globe? Right.

[12:06](https://realalpha.app/v/qGf2Yvan4Wg/?t=726) We actually have this interesting case study. Wiz has this scan for good program where they're actually like actively working with systems across the world to identify, you know, potential issues. And they worked with a hospital system to identify a vulnerability and then patch it. And it's that kind of thing that I think if we can actually leverage these tools to do more of, we can actually make sure that our infrastructure and our systems are robust. Right.

[12:30](https://realalpha.app/v/qGf2Yvan4Wg/?t=750) Which is also, I think, really critical as this whole space grows. There's actually a conversation on All-In this last week about this whole issue that now that AI is getting really good at cyber, people are going to be investing a lot more in cyber defense and AI for protecting. And so there's going to be a lot of money being spent on protecting their systems from this ever smarter AI. So it's really cool that you guys are investing there.

[12:55](https://realalpha.app/v/qGf2Yvan4Wg/?t=775) So I guess just coming back to the question of, do you feel like we'll figure out this concern and this issue we feel, a lot of people feel that AI is going to Take over the world, cause a lot of damage. Do you feel like this is a solvable problem? Are you optimistic or is it something you think a lot about and are kind of worried about?

[13:12](https://realalpha.app/v/qGf2Yvan4Wg/?t=792) Maybe the answer to your question is both in the sense that I think we need to be consistently thinking about it. Right. I think the way to optimism here, for lack of a better way of putting it, like the path to optimism is through thinking about it and being like very careful and very thoughtful and very intentional on the path to get there. And so that is like my source of optimism comes more from Do I feel like we have people who are being intentional and thoughtful about what the safety story looks like?

[13:39](https://realalpha.app/v/qGf2Yvan4Wg/?t=819) And I think that is the critical threat is you need a number of people to be worried and to be having conversations and to be actually interrogating how we're building our models. And that's the step by step process we have to take.