> desperately need LLMs to maintain extremely effective context

Last time I used Gemini it did something very surprising: instead of providing readable code, it started to generate pseudo-minified code.

Like on CSS class would become one long line of CSS, and one JS function became one long line of JS, with most of the variable names minified, while some remained readable, but short. It did away with all unnecessary spaces.

I was asking myself what is happening here, and my only explanation was that maybe Google started training Gemini on minified code, on making Gemini understand and generate it, in order to maximize the value of every token.