Researchers found that distilling a Chinese frontier model (DeepSeek V4 Flash) into a self-distilled model (CTGT 120B) does not transfer censorship, despite training on the same outputs. The self-distilled model outperformed a base model (GPT-OSS-120B) on finance-related tasks, with similar performance to a more advanced Chinese teacher model (DeepSeek V4 Flash). AI summary
Firehose
Filtered to tagged “censorship” · clear filters
Browse: People · Companies · Papers · Podcasts · Hacker News · Deep dives
Browse by tag
artificial intelligence 57continual learning 24agentic coding 21open-weight models 20AI 16AI agents 13reinforcement learning 11cybersecurity 9AI safety 8finance 8language models 7large language models 7open-source 7productivity 7deep learning 6machine learning 6natural language processing 6Reinforcement learning 6tech 6Databricks 5robotics 5software development 5Agentic AI 4benchmarking 4Diffusion models 4multi-agent systems 4Recursive self-improvement 4world models 4AI ethics 3AI infrastructure 3
In this episode, Ada Palmer discusses Niccolò Machiavelli as a deeply patriotic and misunderstood thinker, focusing on the historical context of his work, especially The Prince. They explore Machiavelli's diplomatic career, his views on pow…