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.

This. It's like people collectively forgot about the "misgendering worse than thermonuclear war, founding fathers were black" stuff.

Always go for Grok first for political questions. Other models have such a bad history of being so crudely aligment-hacked, I'd feel like a fool trying to get an impartial answer out of them on some political figure for example.