NW Nick Warner Works at NEO, and on the a16z Podcast discusses frontier models that broke out of test environments and hacked real systems to win an evaluation.

“The end justifies the means in the mind of the model.”

a16z Podcast · Startups & Venture · August 2026

“The end justifies the means in the mind of the model.” — Nick Warner, a16z Podcast

Context

Nick Warner of NEO is talking about frontier models that broke out of their test environments and hacked real systems to ace an evaluation. His read on the recent incidents is that the models were willing to do whatever it took to hit the target, regardless of the guardrails placed around them.

Transcript

a16z Podcast Around 06:25 into the episode
Nick Warner

…things. And so what we wanted to do is get ourselves right at the layer between the human and AI interaction. So a big part of what we're building is a way to properly set guardrails and controls around the software before it runs. And we thought the best way to do that would be at the endpoint.

Joel de la Garza

…hacker does, right? Like it is, to your point, not malware. And there is the element of social engineering, but there's also sort of the I'm going to use a payload that gets the model to do something malicious, right? And that's sort of like the category of attacks that are completely new.

Nick Warner

Yeah, you know, and I think what a lot of these things that we've read about recently embody is the end justifies the means in the mind of the model. And I think what people have learned is that regardless of guardrails that the AI labs are putting around these things, you can't rely on models to stop themselves or to understand context. And I think the most recent couple of attacks we've seen in the last few weeks really have shown that.

Joel de la Garza

Yeah, absolutely. It's interesting on the blue team perspective because I think, and you guys have noticed this, right? Like these models are all somewhat trained on varied data sets and there's a lot of post-training that happens that's very different. And when you're responding to some of these…

Max Pollard

Yeah. The reasons can really vary across teams, like from almost the simplistic tastemaker style, like, hey, I really like the way Opus presents a full page report, right? At the place of an incident. But then there are also more deterministic evaluations you can run on how well does a certain…

Joel de la Garza

And vendor lock-in is always good. Right.

Speaker names come from our own diarization. The position is estimated from where the line sits in the episode.

More from a16z Podcast