LaTeX rendering in DeepResearch output

ChatGPT
,
1

The LaTeX rendering in DeepResearch answers is almost always broken. I like the feature a lot, but it makes it hard to read the output for Math questions.

See e.g. below for an example where even simple formulas like $x$ get bad rendering:

The image is a detailed text discussing the relationship between the archimedean real spectrum and Berkovich analytification, including concepts like projective limits, orderings, and mathematical transformations. (Captioned by AI)
The image is a detailed text discussing the relationship between the archimedean real spectrum and Berkovich analytification, including concepts like projective limits, orderings, and mathematical transformations. (Captioned by AI)755×678 60.1 KB