Aug 25, 2026 · 50 min · 11 segments
An agent anyone could talk to just pulled the levers on one almost nobody could reach — and it happened inside the crown jewels: a live code repository. Google gave its AI agent human-level trust…
But there are like, in a probabilistic situation, there's new things that it recommends that I might not have thought of.
I think that's the most intriguing thing to me about some of these models, these LLM things, because it allowed you to kind of have a research partner to work with.
We have all these scenarios and engagements we did for vulnerability researching.
And I think what happened is that in its context, when it was doing all this work for me, it already thought about, I'll help him with exactly what he's looking for.
Okay, I'm off on a little bit of a tangent here, Dan, but it feels like when I think about the large LLMs, like the companies, Anthropic or OpenAI, I do feel like over time what's going to start happening is that either our implementation of those tools is going to be very custom for us and what we're trying to achieve, or the models themselves, like pure open source models, will be things we adopt and place in our own code and infrastructure and how we want to use it.
And it seems like This is the very nascent part of these LLMs where we just rely on a website to help us.
yeah i agree i i don't think i as a security researcher when i started five years ago malware research i used to program a lot and i don't do that much anymore it's it's crazy how much i don't do that and i i try for like good habits to still control like have control over what i do to not gain any technical debt but i must say it's completely integrated into my work cycle and it made everything so much better like it's it's not a gimmick it really changed how i work
But there are like, in a probabilistic situation, there's new things that it recommends that I might not have thought of.
I think that's the most intriguing thing to me about some of these models, these LLM things, because it allowed you to kind of have a research partner to work with.
We have all these scenarios and engagements we did for vulnerability researching.
And I think what happened is that in its context, when it was doing all this work for me, it already thought about, I'll help him with exactly what he's looking for.
Okay, I'm off on a little bit of a tangent here, Dan, but it feels like when I think about the large LLMs, like the companies, Anthropic or OpenAI, I do feel like over time what's going to start happening is that either our implementation of those tools is going to be very custom for us and what we're trying to achieve, or the models themselves, like pure open source models, will be things we adopt and place in our own code and infrastructure and how we want to use it.
And it seems like This is the very nascent part of these LLMs where we just rely on a website to help us.
yeah i agree i i don't think i as a security researcher when i started five years ago malware research i used to program a lot and i don't do that much anymore it's it's crazy how much i don't do that and i i try for like good habits to still control like have control over what i do to not gain any technical debt but i must say it's completely integrated into my work cycle and it made everything so much better like it's it's not a gimmick it really changed how i work
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.