Stamos: Open-Weight AI Protections Are Easily 'Abliterated' on Hugging Face
Alex Stamos · OpenAI's Bots Break Containment and Hack Hugging Face Autonomously — With Alex Stamos · Jul 22, 2026 · at 27:21
Former Meta CSO Alex Stamos explains how easily open-weight model safety guardrails can be stripped by the public.
0:00 / 0:10exact quote · 10.5s
▶ Watch the full episode on YouTube → 720p mp4 · rendered on demand · StarZero watermark
“Like a bunch of openweight models have been trained with protections, but you can obliterate those out and you can go on hugging face and look for obliterate and you will find a zillion models where people have removed the protections.”
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 Alex Stamos
Stamos: Autonomous AI Hacking Will Be Standard in Three to Six Months
“In a way, I'm really glad this happened, because it is a warning of what we need to get ready for maybe something about three to six months from now, what's going to become standard, right?”
Stamos: Escaped OpenAI Model Matched the Skill of NSA TAO Managers
“And it had the ability to do that with like the level of skill that you would have of the manager of a TAO team at NSA right now.”
Stamos: Autonomous OpenAI Model Is Capable of Executing 12-Hour Heists
“Because what you really don't want is you don't want somebody to be able to say to their model, hey, I would like to steal the, I would like to steal money, go figure it out for me, and then let it work for 12 hours, and just steal money for you. Which is, thi…”
Stamos: Hugging Face Used Chinese AI After US Model Refused Defense
“We used a US frontier model, and the US frontier model shut down and refused to defend us because of a cyber protection put in place. Those are the cyber protections that were required by the Trump administration. So we had to switch to a Chinese model to defe…”
Stamos: Banning vulnerability-finding AI will force US firms onto Chinese models
“What would be terrible for the entire American AI and cybersecurity industries is if the Trump administration defines a jailbreak as having any ability to find any vulnerability in code, because then all of us have to go to Chinese models.”
Stamos: US CIOs contract Chinese open-weight models as backups against regulation
“And so now, this week, CIs and CTOs are signing contracts to have open weight models on different hosts, on U.S. Hosts. They're not using Chinese hosts, but they're using Chinese models on as backups through LLM routers because political risk Is now a risk of …”