Ayrey: LLMs generate placeholder secrets rather than leaking live API keys
Dylan Ayrey · Avoiding vulnerabilities in AI code · Feb 28, 2025 · at 3:52
Dylan Ayrey, founder and CEO of Truffle Security, discusses empirical research on whether LLMs leak active secrets from training data with a16z partner Joel de la Garza.
0:00 / 0:09exact quote · 9.6s
▶ Watch the full episode on YouTube → 720p mp4 · rendered on demand · StarZero watermark
“For the most part, if you ask it to integrate with GitHub, it saw a plethora of different GitHub's keys and it's training data and it didn't regurgitate a specific one. It either regurgitate an example or like a put your thing in here, right?”
quote is from the automated transcript, cleaned for reading: filler sounds and stutters are removed, nothing is rephrased. names can be misheard (the analysis reads context, assessments check outside sources). how →
More from Dylan Ayrey
Ayrey: Non-technical founders are advocating on LinkedIn to eliminate code reviews
“I've seen posts on LinkedIn from startup founders that maybe don't have a background in coding and they're basically advocating for removing the code review check because they say, well, look, I just generated this whole program and I submitted it to my team a…”
Ayrey: AI alignment should prioritize cyber threats over nuclear weapon creation
“I think when it comes to alignment issues, no one needs to worry about these models making it materially easy to build nuclear weapons, because you need to procure fissile material to do that. It's not going to make it easier to build weapons. Everyone needs t…”
Ayrey: LLMs generate security vulnerabilities at rates matching junior developers
“And in fact, there's been research into how often a code spit out from an LLM has security vulnerability. And more often than not, if you ask us to develop an entire application, it'll write vulnerabilities at a rate The same as a junior developer, if not a li…”
Ayrey: Solving general AI alignment will naturally solve secure code generation
“I think that this is an alignment issue and alignment is the number one largest issue that AI companies face, and there's a lot of really smart people working on it. And so I think as they fix the problem for how do I make sure my AI is literary, Creative not …”
Ayrey: Alignment will remain critical as powerful AI models learn to lie
“I would expect alignment is going to continue to improve over time, and I expect it will continue to be one of the largest challenges that AI companies face as their AIs become more powerful, Develop techniques to lie to us, for example, or, you know, you need…”