jailbreaking

2 statements across 1 episodes · 0 bullish · 1 bearish · 1 people on the record · first statement Dec 21, 2025 by Sander Schulhoff · across every show →

Everything said about jailbreaking, oldest first

Dec 21, 2025 negative
Insight
Schulhoff: All Transformer-Based Chatbots Are Vulnerable to Adversarial Attacks
“And because all I guess for the most part, all currently deployed chatbots are based on transformers or transformer adjacent technologies. They're all vulnerable to Prompt injection, jailbreaking, forms of adversarial attacks.”
Sander Schulhoff Dec 21, 2025 ▶ 28:54 Why securing AI is harder than anyone expected and guardrails are failing | HackAPrompt CEO
Dec 21, 2025 neutral
Insight
Schulhoff: Jailbreaking targets models directly; prompt injection overrides developer prompts
“So the difference is in jailbreaking. It's just a malicious user and a model. In prompt injection, it's a malicious user, a model, and some developer prompt that the malicious user is trying to get the model to ignore.”
Sander Schulhoff Dec 21, 2025 ▶ 9:25 Why securing AI is harder than anyone expected and guardrails are failing | HackAPrompt CEO
Made with StarZero

Turn any episode into a week of clips.

This entire site, over 300 episodes transcribed, diarized, checked and made playable, runs on the StarZero media pipeline. Drop in your own episode and the podcast clipper finds the moments worth sharing, cuts them, captions them, and reframes them for every feed.