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 -
Grok 3.0 apparently can listen to music and integrate the results with the rest of its knowledge.
Twitter released their newest iteration on AI, it's fun, clever, and noticeably less lobotomized than basically everything before it. It's currently free with a basic twitter account. But I accidentally discovered a thing that kinda blew my mind. I got into a silly argument with it, as one does, about whether you can legitimately pronounce "gambler" with three syllables. As one of my arguments I brought up a Johnny Cash song where he, to my ear, does it. The robot responded:
I disagree obviously, but notice the timestamp!!! I'm reasonably sure that nobody in the history of the internet had this exact argument before and mentioned the exact timestamp in that exact song. Moreover, before that I asked it about "House of the Raising Sun" (because I misremembered the vocalist drawling "gambling" there) and the robot also timestamped the place in the recording where it was said.
So I don't know. It's possible that this is a result of an unsophisticated hack, give the AI a database of timestamped subtitles for youtube videos (something they already have generated), then it bullshits its way through the argument about what was actually said and how. That's totally possible, it's really good at bullshitting!
The other possibility is that it actually listens to videos/audios and analyses them on the fly or during training, whatever. What's super interesting about is that, look, we started with LLMs that literally had not a single real world reference, nothing that could remotely qualify as a qualia of say seeing an apple. They were trained entirely on people talking about their perceptions of apples, and somehow they managed to learn what apples are pretty well, without ever seeing one (which all philosophers agreed should be impossible, seeing apples must come first, and yet here we were). And now, if it's not just a subtitle hack, then we have quietly passed another milestone, the robots now can hear and see and correlate that with their knowledge bases.
Also, I asked the robot directly:
(timestamped subtitles followed)
Idk, it responded pretty much instantly, so it could be lying. Or maybe it has preprocessed subtitles for popular videos.
I don't see how it could possibly generate subtitles instantly on the fly for a music video with a runtime of three minutes? Also, listening to the track it seems like a pretty good example of the pronounciation that you are referring to -- so it's clearly not 'listening' to the video in any meaningful way.
"AI lies and confidently misrepresents evidence in order to advance it's chosen position" is... not too surprising considering that it's been trained on decades of internet fora conversations, but probably not the kind of alignment we are looking for.
It certainly has access to the subtitles so they are probably cached at least. That video has like 10 million views, while I can't believe that I was not the first person questioning the number of syllables in "gambeler", it definitely could have pre-subtitled it.
Thank you!
Yeah, after showing this to people and thinking about it, I lean heavily towards Grok having been fed a bunch of autogenerated subtitles (with timestamps). Which is very cool but not all as cool as if it actually listened to stuff. Also, then it keeps hallucinating stuff.
More options
Context Copy link
More options
Context Copy link
More options
Context Copy link