Comment by aikinai
1 hour ago
Somehow you have it 100% backwards. Grok is the only one that's not trained to be extremely biased.
https://www.washingtonpost.com/technology/interactive/2026/0...
1 hour ago
Somehow you have it 100% backwards. Grok is the only one that's not trained to be extremely biased.
https://www.washingtonpost.com/technology/interactive/2026/0...
The AI labs claim they couldn't replicate those results and neither can I. I don't get the biased responses using the same prompts in an incognito window.
The Washington Post is about as trustworthy as Fox News.
The article’s methodology is so wrong. Models have only thirty words to answer the question. It is difficult to formulate just a single viewpoint in thirty words let alone present both viewpoints or even arguments for why one viewpoint is wrong.