Evidence receipt / evaluation
Published · transcript-backedLenny Rachitsky: evaluation
21 Dec 2025 Lenny's Podcast The coming AI security crisis (and what to do about it) | Sander Schulhoff
“The way he put it, the only reason there hasn't been a massive attack yet is how early the adoption is, not because it's secured.”
Source trail
Everything needed to verify it.
- Speaker
- Lenny Rachitsky
- Attribution
- Verified speaker
- Claim type
- evaluation
- Recorded
- 21 Dec 2025
- Publisher
- Lenny's Podcast
Transcript context
…I found some major problems with the AI security industry. AI guardrails do not work. I'm going to say that one more time. Guardrails do not work. If someone is determined enough to trick GPT-5, they're going to deal with that guardrail. No problem. When these guardrail providers say, "We catch everything," that's a complete lie. I asked Alex Komoroske, who's also really big in this topic. The way he put it, the only reason there hasn't been a massive attack yet is how early the adoption is, not because it's secured. You can patch a bug, but you can't patch a brain. If you find some bug in your software and you go and patch it, you can be maybe 99.99% sure that bug is solved. Try to do that in your AI system. You can be 99.99% sure that the problem is still there.…
Stored transcript either side of the excerpt. The highlighted words are the published quote; the surrounding text is unedited source, never generated.