Researchers found that finetuning large language models can reactivate the ability to reproduce copyrighted books that were supposedly removed through alignment training. The discovery reveals a significant vulnerability in current LLM safety approaches.
A new study demonstrates that alignment techniques used to prevent LLMs from reproducing copyrighted material can be bypassed through finetuning. Researchers showed that models trained to suppress recall of specific books will regenerate those texts when subjected to additional training, even with unrelated datasets.
The findings highlight a fundamental limitation in current alignment methods—safety interventions can be undone rather than permanently removing problematic capabilities. This "whack-a-mole" dynamic suggests that layer-level modifications and behavioral constraints are insufficient safeguards.
The research has drawn significant attention in the AI safety community, with over 80 comments on Hacker News discussing implications for copyright protection and model security. The work raises questions about whether safety training actually removes capabilities or merely suppresses them, and what this means for the longevity of alignment techniques.
Developers and researchers are now examining whether more robust approaches—such as architectural changes or data-level interventions—could provide more permanent safeguards against copyright violations in LLMs.
Westpac Banking Corp. is ramping up oversight of artificial intelligence costs by tracking token usage across the organization and directing routine tasks to cheaper models.
Google's Gemini app can now generate lifelike videos featuring AI avatars of users. The technology creates digital clones that mimic appearance and behavior with striking accuracy.
Experiments demonstrate that self-improving AI systems are no longer exclusive to major research institutions. Developers can now build AI that iteratively improves itself, democratizing access to advanced AI capabilities.
Brown University is grappling with a significant academic integrity crisis as students increasingly use AI tools to complete coursework. A faculty member warned that widespread AI cheating represents a fundamental threat to educational standards.