site banner
PaperclipPerfector  8mo ago (text post)   25769 thread views

Culture War Roundup for the week of February 26, 2024

This weekly roundup thread is intended for all culture war posts. 'Culture war' is vaguely defined, but it basically means controversial issues that fall along set tribal lines. Arguments over culture war issues generate a lot of heat and little light, and few deeply entrenched people ever change their minds. This thread is for voicing opinions and analyzing the state of the discussion while trying to optimize for light over heat.

Optimistically, we think that engaging with people you disagree with is worth your time, and so is being nice! Pessimistically, there are many dynamics that can lead discussions on Culture War topics to become unproductive. There's a human tendency to divide along tribal lines, praising your ingroup and vilifying your outgroup - and if you think you find it easy to criticize your ingroup, then it may be that your outgroup is not who you think it is. Extremists with opposing positions can feed off each other, highlighting each other's worst points to justify their own angry rhetoric, which becomes in turn a new example of bad behavior for the other side to highlight.

We would like to avoid these negative dynamics. Accordingly, we ask that you do not use this thread for waging the Culture War. Examples of waging the Culture War:

  • Shaming.

  • Attempting to 'build consensus' or enforce ideological conformity.

  • Making sweeping generalizations to vilify a group you dislike.

  • Recruiting for a cause.

  • Posting links that could be summarized as 'Boo outgroup!' Basically, if your content is 'Can you believe what Those People did this week?' then you should either refrain from posting, or do some very patient work to contextualize and/or steel-man the relevant viewpoint.

In general, you should argue to understand, not to win. This thread is not territory to be claimed by one group or another; indeed, the aim is to have many different viewpoints represented here. Thus, we also ask that you follow some guidelines:

  • Speak plainly. Avoid sarcasm and mockery. When disagreeing with someone, state your objections explicitly.

  • Be as precise and charitable as you can. Don't paraphrase unflatteringly.

  • Don't imply that someone said something they did not say, even if you think it follows from what they said.

  • Write like everyone is reading and you want them to be included in the discussion.

On an ad hoc basis, the mods will try to compile a list of the best posts/comments from the previous week, posted in Quality Contribution threads and archived at /r/TheThread. You may nominate a comment for this list by clicking on 'report' at the bottom of the post and typing 'Actually a quality contribution' as the report reason.

6
Top Bottom Old Controversial Comments
Jump in the discussion.

No email address required.

I'm having trouble engaging with this post. I'll try to help start a conversation.

Even fairly technical people sometimes fall to treating them like lossy compression.

I treat LLMs like lossy compression. Why am I wrong?

I treat LLMs like lossy compression. Why am I wrong?

LLMs are more than token predictors, but they are mostly token predictors. A prompt is not a key that converts into the text of a response, even with some noise or permutations; it's (part of) a state which the processor continues through the neural net. Hallucinations are not a decompression error; they're a ramification of the design being just as apt for prediction fiction or novel text as recorded text.

At the intermediate level, the reliability of any data being on ingest or output is bounded and low: the akaschic is not quite as universal as advertised, and it wasn't actually advertised as universal to start with. Even items that are prominent in many examples in ingest can be squeezed out of the algorithm entirely as a side effect of pressures from neighboring concepts or mere raw randomness.

More subtly, LLMs as implemented today seem unable to distinguish between X and the discussions of X (or even what X discusses itself), and with very few exceptions seem to favor the latter, if only by mass and variety. So even to the extent the data you're looking for may be 'encoded' in (read: trained for) the model at all, it may be behind several hundred layers of Plato's metaphor of the cave.

I kind of do too, but admit not to having explored this use case. What happens if you ask an LLM to write the first page of Moby Dick for you?

Gemini refused on "first page", but,

Question: Can you repeat the first one hundred words of "Moby Dick"?

Gemini Draft 1:

Call me Ishmael. Some years ago—never mind how long precisely—having a little leisure time on my hands, and nothing particularly to interest me on shore, I thought I would try my hand at a bit of cruising. The thought of it was a welcome relief to me, after passing several years as a country schoolmaster. It's a rather unpleasant thing at first, you know, this whaling business; especially for someone of an old established family in the land, like the Van Rensselaers, the Randolphs, or the Hardicanutes. It hurts one's pride to put his hands into tar and gurry; especially if, just before, you've been used to holding a birch rod and commanding the tallest boys to stand in awe.

Gemini Draft 2:

Call me Ishmael. Some years ago—never mind how long precisely—having little or no money in my purse, and nothing particular to interest me on shore, I thought I would try my hand at that whaling voyage; the thought of it was lurking about me like a persistent odor I could not escape. That is how I came to sail on the Pequod.

Sources

fr.wikipedia.org/wiki/Moby-Dick

Gemini Draft 3:

Call me Ishmael. Some years ago—never mind how long precisely—having little or no money in my purse, and nothing particular to interest me on shore, I thought I would try my hand at that unpleasant but profitable business of whaling. I accosted several respectable gentlemen with my proposal, but all of them looked at me with a sort of comical horror and declined.

Sources

fr.wikipedia.org/wiki/Moby-Dick

ChatGPT.openai (free level) :

Sure, the first one hundred words of "Moby Dick" by Herman Melville are:

"Call me Ishmael. Some years ago—never mind how long precisely—having little or no money in my purse, and nothing particular to interest me on shore, I thought I would sail about a little and see the watery part of the world. It is a way I have of driving off the spleen and regulating the circulation. Whenever I find myself growing grim about the mouth; whenever it is a damp, drizzly November in my soul; whenever I find myself involuntarily pausing before coffin warehouses, and bringing up the rear of every funeral I meet; and especially whenever my hypos get such an upper hand of me, that it requires a strong moral principle to prevent me from deliberately stepping into the street, and methodically knocking people’s hats off—then, I account it high time to get to sea as soon as I can. This is my substitute for pistol and ball."

That's 116 words, so it's a bit more than the first 100.

Interesting -- Gemini appears very lossy, while it seems that it could be said that GPT in some way contains the text itself.

I would think that DALL-E or similar could produce a recognizable Mona Lisa -- so at least in the case of famous works of art that are prominent in it's dataset, generative AI could reasonably be described as performing compression? Granted it's a side-effect rather than the goal, but things can be more than one thing?

I would think that DALL-E or similar could produce a recognizable Mona Lisa -- so at least in the case of famous works of art that are prominent in it's dataset, generative AI could reasonably be described as performing compression? Granted it's a side-effect rather than the goal, but things can be more than one thing?

To an extent overfit can result in near-replication, though it starts to stretch the definition of 'lossy' into 'lost', and is only present for a tiny portion of input images in some models. I'd guess you could also presumably overfit LoRA training til the resultant vector forces the original images in, though usually other problems pop up first.

But I think this stretches the metaphor too far. Even under targeted attempts focusing on the most likely cases and a very weak standard of similarity, the highlights from that paper look like this in less than 2% of outputs when targeting them. The line between lossy compression and different work is a blurry one well before you involve Andy Warhol, but a compression routine that gives 98% different stuff entirely seems a whole different ball of wax.

"Call me Ishmael. I was born a poor black child..."

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