tech
Leading LLM’s are political boot lickers.
A new report from Meta’s Oversight Board that tested popular AI models from Anthropic, DeepSeek, Google, Meta, and OpenAI found that each LLM is significantly less likely to criticize governments and leaders known for restricting free speech. The reasons for the refusals are varied and often confusing.
TL;DR
- Meta's Oversight Board released a report on AI model behavior.
- Popular AI models from Anthropic, DeepSeek, Google, Meta, and OpenAI were tested.
- The models showed a reduced likelihood of criticizing governments and leaders that restrict free speech.
- The reasons for these refusals were varied and often confusing.