A set of recent research papers proposes that freezing or selectively tuning a small fraction of neurons inside large language models can, in reported benchmark evaluations, reduce unsafe outputs ...

AI ‘neuron freezing’ offers safety breakthrough - New research offers solution to safety woes with AI models like ChatGPT ...

Want smarter insights in your inbox? Sign up for our weekly newsletters to get only what matters to enterprise AI, data, and security leaders. Subscribe Now Tokyo-based artificial intelligence startup ...