[pessimizer]

I don't know what you're seeing here. They only did this with a couple of points that were very close to each other, and didn't change their horizontal position. That, and the rest of the tables, also made it very clear that Chatgpt and Grok were almost mirrored based on the particular wedge issues that were shown. Makes it pretty obvious that aggressive tweaking is happening with both.

The Deepseek example somehow makes the Chatgpt/Grok tweaking even more obvious, because it's a list of things that China doesn't care in an extreme way about (or holds its position confidently), and a question about drugs, which it does care about (and I think feels less confident about.)

China's antidrug feeling is just a mix of the historical repulsion about English control of China through drug dealing and waging war to support it, and a world zeitgeist that supported a lot of crazy antidrug policy in the developing world because it offered a way for the US to smuggle a bunch of currency and military aid into your politics. It's not rational, and most of China's policies are. It's a relic. Hence the thumb on the scale.

[Cakez0r]

I'm seeing that the headline chart of the article is inexplicably deceptive. Why not use coloured data points and a legend? If you're going to have logos with lines pointing to the data points, why make the data points and lines feint grey so that they're barely visible? Why does grok have a comically long line extended out to the right of its data point when every other logo is positioned below its data point? You could say it's an honest mistake, but this whole article reeks of "Elon bad" astroturfing.

[verteu]

Here's what I see on desktop: https://i.imgur.com/vuA2Y3w.png

Is this an artifact of dynamic resizing at small resolutions?