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.
Jump in the discussion.
No email address required.
Notes -
Against Large Language Models as an Archive
Much of the recent discussion regarding token-predicting AI such as LLMs has revolved around the intentional (and often-hilariously heavy-handed) political and social modification of these tools, their inputs, and their outputs, and there's a lot of interesting questions there. Separately, though, one space that appears under-examined is what, exactly, LLMs do when handling questions that aren't the hottest topics at the time the LLM was trained.
There's a lot of people who think, at some level, of LLMs as a .zip file++, where material is stuffed in somehow and the core meaning is pulled out from the text. Even fairly technical people sometimes fall to treating them like lossy compression, and there's already an active lawsuit caused in part by people expecting a ChatGPT to act as one. They do better when told to reparse existing information, but the people advocating that also promote LLMs as providing "pre-digested" Google answers. But in theory, these tools have been trained on a large portion of text from a massive variety of sources, and they can sometimes embed even tiny historical details.
Though you sometimes have to handle seers huffing fumes, the 12v universal akasha sometimes works. In reality, LLMs are token predictors, and they've been trained, and sometimes they just do that well instead. And sometimes it doesn't at all.
And I think that's going to augment forces that already turn memories to dust.
[Previous discussion here and, by another poster, here].
It's difficult to draw the borders around this limitation. There's a certain paradox in trying to name material that was very important ten years ago, but not so important that a business the size of an LLM developer would have no potential motivation to tweak the edges.
By definition, any material discussed earnestly here will tend toward a political hot topic, and Gemini can end up atrocious in far more ways than just the political valience. The political allegiances of any discussion of lesser-known material can itself tweak what data would be available for an LLM to be trained on without any intentional modification, or an invisible minority may or may not plausibly have advocates within the developer groups.
Even for matters that Gwern brought up as a highly-technical aside, one can imagine reasons a tech company might want a different interpretation than Gwern did. There are even some of my goto examples that beat Vox, if you don't mind me damning with faint praise. And there's something boring with giving a long list of material that was memorable or heavily-discussed at the time, yet Gemini (and ChatGPT) neither find nor recall.
((Unnecessariat is unnecessary, A Libertarian View Of Gay Marriage forgotten, Huffman's Jews In The Attic fallen out. Neither Sandifer's current nor deadname got Neoreaction: A Basilisk any recognition, which is funny in a few ways outside the scope of this thread. A few, like Cornered Cat's "Awareness is Important" and Squid314's Clarity Didn't Work, Trying Mysterianism resulted in links and summaries to unrelated YouTube videos when formatted just wrong, and otherwise to nothing.))
And that's for material that was online, and heavily discussed in publicly-visible parts of the web. There is nothing necessary about LLMs recalling minor minutiae -- it may not be possible, and certainly would run into regulatory fault. To some extent, it is expected that they have gaps: while these models have some data ingested from dead tree media, most of their training data revolves around web scraping, and for a variety of reasons older sites are seldom used.
But there are risks to integrating too heavily with even the best systems that have your interests in mind. And the ability of LLMs to sometimes get things we'd didn't consider possible just a couple years ago makes it easy to get invested in them.
I'm having trouble engaging with this post. I'll try to help start a conversation.
I treat LLMs like lossy compression. Why am I wrong?
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:
Gemini Draft 2:
Gemini Draft 3:
ChatGPT.openai (free level) :
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?
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.
More options
Context Copy link
More options
Context Copy link
More options
Context Copy link
More options
Context Copy link
More options
Context Copy link
More options
Context Copy link