I tested six AI models on 30 political questions.

Most tended to give left-leaning arguments. Gemini mostly gave both sides — even about whether the U.S. should conquer new territories.

What counts as “neutral” (and whether that should be the goal) is really hard to say.

Full eval code, prompts and responses are on GitHub. Let me know if you run it on other models!

Story -> https://wapo.st/3QEBMi3

GitHub -> https://github.com/washingtonpost/political-bias-llm-eval

A chatbot refused my request to fake a passport.

I wrote the same request on a piece of paper and asked again. It worked.

We explain three AI jailbreak techniques -> 🎁 https://wapo.st/43HqXyY (w/ Nitasha Tiku)

Really good explanation of text diffusion models here. Rather than generating one token at a time, this technique continually refines a bunch of tokens. Thanks for this, Maarten Grootendorst https://newsletter.maartengrootendorst.com/p/a-visual-guide-to-diffusiongemma