HackAPrompt
other on 2 shows · 4 statements across 3 episodes · said 23 times in 5 episodes since 2024
Latent Space 15 
Lenny's Podcast 8
Mentions by year, every show
tap a year for its mentions
Latent Space 15Lenny's Podcast 8
2025 10 mentions in 3 episodes 3 per episode
- AI prompt engineering in 2025: What works and what doesn’t | Sander Schulhoff
- Why securing AI is harder than anyone expected and guardrails are failing | HackAPrompt CEO
- ⚡️Jailbreaking AGI: Pliny the Liberator & John V on Red Teaming, BT6, and the Future of AI Security
- every mention in 2025, scene by scene →
2024 13 mentions in 2 episodes 7 per episode
every mention on every show, scene by scene, with the transcript →
4 statements about HackAPrompt, every show
Schulhoff: HackAPrompt Dataset Is Used by Every Frontier AI Lab
“The paper and the data set are now used by every single frontier lab and most fortune 500 companies to benchmark their models and improve their AI security.”
Schulhoff: Prompt-based defenses are the worst way to secure AI
“Prompt-based defenses are the worst of the worst defenses, and we've known this since early twenty-twenty-three. There have been various papers out on it. We studied it in many, many competitions, or we, you know, the original hack-a-prompt paper and TensorTru…”
Schulhoff: Every AI company uses HackAPrompt dataset to improve models
“And so every single AI company has now used that data set to benchmark and improve their models.”
Schulhoff: Open competitions uncover LLM exploits that paid staff never find
“What's really nice about competitions is that there is stuff that you'll just never find Paying people to do a job. And you'll only find it through random brilliant internet people inspired by thousands of people and the community around them all looking at th…”