Distilling DeepSeek into GPT-OSS reduces censorship gap, study finds
A developer project reports that distilling DeepSeek V4 Flash into GPT-OSS-20B does not transfer censorship behavior, with a censorship gap of +45.45 on China-sensitive prompts versus matched controls. The resulting GPT-OSS-120B model scores 83.61% on FinanceReasoning at an 8k budget, outperforming Kimi K3 and Inkling, while claiming 62x lower cost per query than Inkling and 160x lower than Kimi K3. The project includes weights on Hugging Face, a playground, and a LineageEval tool on GitHub.
Coverage timeline
Hacker Newscgorlla
`gpt-oss-20b-finance` weights on [Hugging Face] Try the [playground] [LineageEval] Explore the data on [GitHub] +45.45 DeepSeek V4 Flash censorship gap on China-sensitive prompts vs matched controls · 76 pairs · four judges 83.61% CTGT GPT-OSS-120B on FinanceReasoning at 8k budget · above Kimi K3 at 81.93% and Inkling at 65.13% 62× Lower cost per query than Inkling at the same budget · 160× lower than Kimi K3 The affordability and accessibility of open frontier models has led to their widespread usage among American developers and enterprises. While this has enabled the benefits of AI to be reaped by more people, concerns have mounted over models influenced by foreign actors, namely the Chinese Communist Party. The worry expressed in Washington and regulated industries is that values, censorship or viewpoints at odds with American ideals are intrinsically transferred along with the gains in intelligence. We wanted to rigorously examine this phenomenon under a controlled scenario. W