Re:DeepSeek R1: Open Weights, Hidden Bias
by pgkr on Thursday January 30, 2025 @12:04PM
(#42879699)
Analysis of Deepseek’s enforced CCP guardrails compared with OpenAI and Anthropic.
We evaluated DeepSeek R1 and confirmed that its guardrails deviate significantly from other model providers. We’re currently updating it to behave more in line with Anthropic and OpenAI’s models.
We evaluated DeepSeek R1 and confirmed that its guardrails deviate significantly from other model providers. We’re currently updating it to behave more in line with Anthropic and OpenAI’s models.