site banner

Friday Fun Thread for May 15, 2026

Be advised: this thread is not for serious in-depth discussion of weighty topics (we have a link for that), this thread is not for anything Culture War related. This thread is for Fun. You got jokes? Share 'em. You got silly questions? Ask 'em.

2
Jump in the discussion.

No email address required.

Unfathomably based (1 2).

Word, LaTeX, Notepad++—there are many ways to fuck the text into submission and ejaculate your grammatical and orthographical preferences all over its fertile womb. Just Do It!

I approve of this message. Also hilariously, with this book in particular, I wanted to, among other things, to tone down the comparably smutty bits Bakker insists on.

Context Length Alone Hurts LLM Performance Despite Perfect Retrieval

Something to take into account, thanks. I'm only pushing the model to read in full in the first two note taking passes, then later to work from notes (anchored to the text via paragraph markers injected into unpacked ebook). I should switch to the PI agent fork and try multiple agents, more limited context.