site banner
PaperclipPerfector  2d ago (text post)   1470 thread views

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.

1
Top Bottom Old Controversial Comments
Jump in the discussion.

No email address required.

What fun thing are you doing with AI?

Experimenting with selective edits on books - partially expunge a plotline, remove inner life of a character, paper over a plothole and try to keep it consistent later, remove repetitive passages. No results yet, only hours of fiddling with workflow - trying to get it to make decent notes ("The User is right, I read 8 chapters but the note file is empty. This is bad.") or keep it reading in full without it deciding to start skimming was fun. Getting a feeling this may be too complex of a task to get right with a few naive prompts if the goal is first to build extensive understanding of the books read, not just do smart find&replace.

Third book of Prince of Nothing was the trigger.

not gentle fixfic, but brutal nonconsensual editing

Unfathomably based (1 2).

trying to get it to keep it reading in full without it deciding to start skimming

Paper:

Context Length Alone Hurts LLM Performance Despite Perfect Retrieval

Our systematic experiments across five open- and closed-source LLMs on math, question answering, and coding tasks reveal that, even when models can perfectly retrieve all relevant information, their performance still degrades substantially (13.9–85 %) as input length increases but remains well within the models' claimed lengths.

See table 2.

Nvidia investigation

Despite achieving nearly perfect performance on the vanilla needle-in-a-haystack (NIAH) test, most models exhibit large degradation on tasks in RULER as sequence length increases.

Funny quote:

What is the current largest context window for an open LLM?

Does not matter as all these long-context models develop dementia when using 10 % of their context window.

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.

What is this place?

This website is a place for people who want to move past shady thinking and test their ideas in a court of people who don't all share the same biases. Our goal is to optimize for light, not heat; this is a group effort, and all commentators are asked to do their part.

The weekly Culture War threads host the most controversial topics and are the most visible aspect of The Motte. However, many other topics are appropriate here. We encourage people to post anything related to science, politics, or philosophy; if in doubt, post!

Check out The Vault for an archive of old quality posts. You are encouraged to crosspost these elsewhere.


Why are you called The Motte?

A motte is a stone keep on a raised earthwork common in early medieval fortifications. More pertinently, it's an element in a rhetorical move called a "Motte-and-Bailey", originally identified by philosopher Nicholas Shackel. It describes the tendency in discourse for people to move from a controversial but high value claim to a defensible but less exciting one upon any resistance to the former. He likens this to the medieval fortification, where a desirable land (the bailey) is abandoned when in danger for the more easily defended motte. In Shackel's words, "The Motte represents the defensible but undesired propositions to which one retreats when hard pressed."

On The Motte, always attempt to remain inside your defensible territory, even if you are not being pressed.


New post guidelines

If you're posting something that isn't related to the culture war, we encourage you to post a thread for it. A submission statement is highly appreciated, but isn't necessary for text posts or links to largely-text posts such as blogs or news articles; if we're unsure of the value of your post, we might remove it until you add a submission statement. A submission statement is required for non-text sources (videos, podcasts, images).

Culture war posts go in the culture war thread; all links must either include a submission statement or significant commentary. Bare links without those will be removed.

If in doubt, please post it!


Rules


Recommended Posts And Communities

Recommended Realtime Chats