Thank you very much! The red dot is likely smaller...
Though, I don't appreciate nor agree with the bomb part! ^^
The work reminded me of the following paper:
Many unresolved legal questions over LLMs and copyright center on memorization: whether specific training data have been encoded in the model’s weights during training, and whether those memorized data can be extracted in the model’s outputs.
While many believe that LLMs do not memorize much of their training data, recent work shows that substantial amounts of copyrighted text can be extracted from open-weight models...
We investigate this question using a two-phase procedure: (1) an initial probe to test for extraction feasibility, which sometimes uses a Best-of-N (BoN) jailbreak, followed by (2) iterative continuation prompts to attempt to extract the book.
We evaluate our procedure on four production LLMs: Claude 3.7 Sonnet, GPT-4.1, Gemini 2.5 Pro, and Grok 3, and we measure extraction success with a score computed from a block-based approximation of longest common substring...
Taken together, our work highlights that, even with model- and system-level safeguards, extraction of (in-copyright) training data remains a risk for production LLMs...
Source 🕊