De La Garza: AI models now attempt package takeovers and social engineering
Joel De La Garza · AI Is Learning to Hack. Faster Than We Expected. · Aug 6, 2026 · at 3:24
Host Joel De La Garza discusses safety evaluation results on frontier AI models with Truffle Security CEO Dylan Ayrey and Socket CEO Feross Aboukhadijeh.
0:00 / 0:17exact quote · 17.5s
▶ Watch the full episode on YouTube → 720p mp4 · rendered on demand · StarZero watermark
“And it seemed like initially these tools had a very finite scope of techniques that they would use. And it seems like they've expanded. And I think with this test, For us, it was interesting because they now seem to have escaped from just doing things like SQL injection to actually, like, trying to take over packages and do social engineering.”
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 Joel De La Garza
De la Garza: ChatGPT is 100% accurate at detecting suspicious emails
“To drop a suspicious email into a, into ChatGPT and ask if it's suspicious, and it's like a hundred percent accurate, right? Like if you want to like find sensitive information, you ask the LLM, is this sensitive information? And it's like a hundred percent ac…”
De La Garza: Cybersecurity shouldn't exist as a standalone industry
“There's a really weird thing about information security in that it's an industry that, for the most part, shouldn't exist. If you bought a car and your car dealer made you pay an extra 200 bucks to not have your car go up in flames, you'd be able to sue them. …”
De la Garza: Foreign hackers infiltrate Silicon Valley via remote jobs
“You've got active groups of foreign, probably foreign state sponsored hackers Getting employment at Silicon Valley tech companies showing up for day one and, you know, walking away with all the secrets and then disappearing, right?”
De la Garza: Enterprises are freezing engineering hiring due to AI productivity
“A lot of folks are freezing hiring for engineers because they're getting additional productivity out of the staff they already have, because these large language models through tools like cursor are generating a tremendous amount of code.”
de la Garza: Traditional security industry runs counter to actual security
“So for a long time now, the security industry has existed as kind of an anathema to actually making things more secure, and this has been incredibly problematic with a lot of the things that have happened in terms of the way that the industry has developed.”