DeepSeek R1: Open Weights, Hidden Bias

https://blog.getplum.ai/Deepseek-R1-Open-weights-Hidden-bias-18933807f8d08002a18ff42ba343a432

by pgkr • 1 year ago

11 7 1 year ago

blog.getplum.ai

pgkr4• 1 year ago

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.

sylware3• 1 year ago

The bias is baked into the open weights, namely happening on self-hosted 671B LLM??

pgkr4• 1 year ago

Yes -- we observed this behavior on both the open-source open-weights 671B model as well as the DeepSeek web app.

sylware3• 1 year ago

Weird, because I got some deepseek feedback where it was openly critical and explicit about the authoritative regime of china. I really thought it was the "deepseek web app" only.

Then I have mixed signals about this.

DeepSeek R1: Open Weights, Hidden Bias

Related Stories