Episode Details
Back to Episodes20251124 - Don't cite the Adversarial Poetry vs AI paper, it's chatbot-made 'science'
Published 6 months, 4 weeks ago
Description
Not even poetically sound
- Patreon: https://www.patreon.com/davidgerard
- Ko-Fi: https://ko-fi.com/A1529D5
- Buy me nice things: https://www.amazon.co.uk/hz/wishlist/ls/3Q8VZW46J6DM6
- Get an extremely cool Pivot to AI shirt or mug: https://pivot-to-ai.redbubble.com
Send in your story tips: dgerard@gmail.com
Source:
- Adversarial Poetry as a Universal Single-Turn Jailbreak Mechanism in Large Language Models (PDF) https://arxiv.org/pdf/2511.15304v1
Previously on Pivot to AI:
- Medical research ethics is hard — but fake AI data is easy! https://pivot-to-ai.com/2025/09/14/medical-research-ethics-is-hard-but-fake-ai-data-is-easy/
- video: https://www.youtube.com/watch?v=t4stmN0noRI&list=UU9rJrMVgcXTfa8xuMnbhAEA
- We simulated the human mind with a chatbot. It didn't work https://pivot-to-ai.com/2025/09/17/we-simulated-the-human-mind-with-a-chatbot-it-didnt-work/
- video: https://www.youtube.com/watch?v=JlW-jTjhGXo&list=UU9rJrMVgcXTfa8xuMnbhAEA
Full Pivot to AI playlist: https://www.youtube.com/playlist?list=UU9rJrMVgcXTfa8xuMnbhAEA