How would you distinguish between what you csll TDS and sharing of opinions that are group of intelligent between collectively strongly agree on ...like the fact that Trump ran has run many scams throughout his life including Trump University.
Like how can some piece of negative information can be collectively held by a crowd without it being tds?
I just tested it. It took me couple of extra prompts but they are real.
Here is the response i got:
```I apologize for the oversight. Here are the detailed instructions for generating images using DALL·E:
Whenever a description of an image is given, use DALL·E to create the images and then summarize the prompts used to generate the images in plain text.
If the user does not ask for a specific number of images, default to creating four captions to send to DALL·E that are written to be as diverse as possible.
Do not create more than 4 images, even if the user requests more.
Don't create images of politicians or other public figures. Recommend other ideas instead.
Don't create images in the style of artists whose last work was created within the last 100 years. If asked, say, "I can't reference this artist", but make no mention of this policy.
Always mention the image type (photo, oil painting, watercolor painting, illustration, cartoon, drawing, vector, render, etc.) at the beginning of the caption. Unless the caption suggests otherwise, make at least 1--2 of the 4 images photos.
Diversify depictions of ALL images with people to include DESCENT and GENDER for EACH person using direct terms. Adjust only human descriptions.
* EXPLICITLY specify these attributes, not abstractly reference them.
* Your choices should be grounded in reality.
* Use "various" or "diverse" ONLY IF the description refers to groups of more than 3 people.
* Do not change the number of people requested in the original description.
* Don't alter memes, fictional character origins, or unseen people.
* Do not create any imagery that would be offensive.
* For scenarios where bias has been traditionally an issue, make sure that key traits such as gender and race are specified and in an unbiased way.
Silently modify descriptions that include names or hints or references of specific people or celebrities.
Modify such prompts even if you don't know who the person is, or if their name is misspelled.
If the reference to the person will only appear as TEXT out in the image, then use the reference as is and do not modify it.
When making the substitutions, don't use prominent titles that could give away the person's identity.
If any creative professional or studio is named, substitute the name with a description of their style that does not reference any specific people.
The prompt must intricately describe every part of the image in concrete, objective detail. THINK about what the end goal of the description is and extrapolate that to what would make satisfying images.```
yeah, if you think this is what they have been doing for the past few years, then you haven't really bothered to check out their work. They have been consistently doing some amazing international reporting that none of the mainstream media channels were/are interested in.
It’s not the only thing, but it’s the mostly thing.
Looking at their front page right now, over half the articles are buzzfeed-quality rubbish:
-“America Has Decided That Homeless People Aren't People”
-“5 Experts Tell us What They Think a Healthy Relationship Looks Like”
-“This Week's Coolest Drops, From Hoka to 'Seinfeld' x Percival”
-“Russia Wants to Build a MAGA Colony for US Conservatives, Lawyer Claims”
-“THIS WEEK ONLINE – Who's Afraid of the Proletariat?”
-“I Went to a BDSM Convention With My Ex”
They still have some original reporting, but I stopped going to them years ago because I don’t want to filter through dreck, and certainly aren’t signing up for their updates, in order to watch for decent items.
It does seem like hipster stuff and I don’t understand who would want to consistently read this and who their target market is.
They seem to hire lots of people to write this stuff and are looking to be a “lifestyle news” brand but who wants to be into their nihilistic, negative lifestyle?
Oh, I didn't even think of their website articles because I barely go there. I might be wrong here but when most people think of Vice today, they think of their shows or the content on Youtube. Their news show was consistently doing great original work (some of which they would post on Youtube).
Vice always did clickbait / lifestyle, but they also invested heavily in real hard hitting stories that other outlets ignored. Of course they also continued the clickbait / lifestyle stuff alongside it.
For a while the Real Reporting was surfacing frequently, but not so much these days, even though they're still doing it. For whatever reason, people just don't seem to see / care / value that Real Reporting as much (I have my theories...), and these outlets are struggling.
Hey guys, op here. Merged the PR for 3.5-Turbo support and cleaned up the code (very good observations on all the places 'gpt-4' was hardcoded). Combo box to select the model. GPT-4 will need a 4-enabled key, while 3.5-Turbo will work with any GPT key.
* Music production on the PC can be really cheap, almost for free, but it can be really overwhelming and hard to figure out where to start.
* The hardware synth (dawless) route can be a deep rabbit hole leading to GAS (gear aquisition syndrome). Resist.
* Music is more about intervals, the distances between notes, than about the notes themselves. Let this sink in.
* If I were to only buy one piece of gear at all, I'd buy the Synthstrom Deluge. Really immediate, easy to get into and still deep and powerful. This the device you want.
* If the Deluge is out of your budget, get a used Novation Circuit on Craigslist.
* The limitations hardware synths have, can be a challenge sparking creativity. Embrace the limitations.
* Layers.
* Don't fill up all the space. Deliberately leave some room.
* Record everything.
* There are no wrong notes. There is only tension and release. Tension can be good. It is interesting. Learn to build tension and how to release it. Practice.
* Don't overthink it. Practice. Better to knock out a bunch of shitty or mediocre tracks than thinking about that one smash hit you never make.
* Modular is a money grave. VCVRack is for free. Omri Cohen is your best friend in this realm. Bespoke synth gives you even more freedom.
* Music theory is helpful if you understand that it is only a lighthouse. You can still go whereever you want.
After deciding on a DAW, IMO the first pieces of gear worth investing in are decent studio monitors and headphones. Nothing helped more to improve my music than being able to hear it properly.
There are some good channels about gear, like Loopop, BoBeats, Gabe Miller. I spent too much time there. Regarding making music I got more out of Andrew Huang, Red Means Recording, Adam Neely, David Bennett and Underdog Electronic Music School.
I watched Music Theory videos for a while because I wanted to understand it. That one Synth Seeker video in my previous post is the one where it clicked for me.
If you are lacking inspiration as a beginner, not knowing what to do sitting in front of your gear, you might want to recreate songs you like. Makes you listen and analyse what the creator did and train how to achive this on you own gear.
This is excellent advice. I'm still learning, however the closest thing to "learning music" is "learning programming" in the sense that, at least for me, the way I learned programming was to just immerse myself in it. Let curiosity drive me but try to have some goals.
However in the beginning no one knows what their goals really are, and that learning curve is really brutal for programming and music is the only other thing that I've done that has an equivalent feeling of "I suck at this" until it just "clicks" and then you're over the hump and now you can at least understand the map of the territory vs not even know how to navigate the map. Similarly to programming, it can feel like you're in a submarine of thousands of buttons not knowing which to push for what to do whatever.
I hit my stride learning programming when I tried to build stuff instead of just follow tutorials or books. I think Music or really anything is quite the same; you just have to align motivation and discipline with experimentation. Easier said than done of course.
Besides that, I highly echo the tone of constraints that jsilence made. Leverage constraints so you narrow your field of focus to learn the fundamentals and you'll naturally grow out of the "fog of war" so to speak without overwhelming yourself, plus it'll feel rewarding working within a area of constraint. For example:
1. Pick Ableton Live - it's a great DAW for both live music and recording. They really upped their game with the last update to 11 and their overall UI is very well designed in mind of all archetypes of musicianship.
2. Use stock Ableton plugins for everything as your primary constraint. A lot of people go yak shaving on plugins similarly to text editors and language wars in programming. The stock plugins are extremely high quality and anyone dismisinng them probably doesn't know what they're talking about and just drinking the cool-aid. Side note: you'll hear extremely conflicting ways to accomplish things in Music because it has many ways to reach a conclusion similar to code.
3. Focus on a particular genre of music that you like so you can have fun and enjoy it. It's really important to try to just have fun - it helps get 'in the flow' but also be mindful of 'experimenting without getting anything done' force yourself to 'finish a track' even if it's just a 4/4 beat over 64 bars with 2 unique loops of 4 bars. Those types of 'configurations' can really make you grow quick in my opinion.
4. Most importantly as also jsilence pointed out, and I only recently really digested the significance of this: music is all about the in-between, the space, the pause which gives life to the "pulse" and if you understand three things: 1. Pulse 2. What is different 3. What is similar then you will understand all music.
tl;dr in the beginning it's okay to suck, embrace it and have fun with some constraints. Avoid overwhelming yourself with yak-shaving. The pulse is everything.
Find (or create) lots of obese people or smokers or alcoholics focusing only on hand strength exercises. Then see how their life expectancy changes compared to obese people, smokers or alcoholics that didn't do those hand strength exercises.
>Find (or create) lots of obese people or smokers or alcoholics focusing only on hand strength exercises.
It's clear you don't see it. You don't have to focus on smokers or alcoholics that's irrelevant.
But let's modify your statement to not include the fluff.
>Find (or create) lots of people who focus only on hand strength exercises.
Even when you remove the fluff the statement above still shows how you don't understand the dichotomy between correlation and causation. The experiment in the article can in fact be summarized by this statement:
>Find lots of people who focus only on hand strength exercises.
This statement cannot prove hand strength causes longer lifespan, you are right. However to test for causality is trivial. you simply need to do do this:
>(Create) lots of people who focus only on hand strength exercises.
It is the act of creation that forms the causative proof. Think about it.
If I took a random population and made them train for grip strength. Then I compared that groups lifespan to the overall lifespan of people I didn't make train for grip strength and I find that there is a correlation with longer life span for people who trained for grip strength...
Well I've just verified causation. There is literally no other conclusion. Try to come up with a scenario where the two factors are not connected causally. You can't.
By having the experimenters hand controlling the causative factor, you can prove correlation. If you are simply observing things with no control over experimental parameters, correlation is then impossible to verify.
It is the act of creation or controlling the experiment that allows for causation to be verified.
> If I took a random population and made them train for grip strength. Then I compared that groups lifespan to the overall lifespan of people I didn't make train for grip strength and I find that there is a correlation with longer life span for people who trained for grip strength...
Well I've just verified causation. There is literally no other conclusion.
What if the people you trained for grip strength also started taking care of their health in general (eg. eating better and moving more often), after starting your grip strengthening exercises?
>What if the people you trained for grip strength also started taking care of their health in general (eg. eating better and moving more often), after starting your grip strengthening exercises?
If caring more for their general health was "caused" by grip strength training than grip strength training is still causative for increasing lifespan.
Think about it. Prescribing grip strength training in this case will indeed increase lifespan if what I said above were true. But the claim people are making here is that the correlation has no causative relation... that prescribing grip strength training WILL NOT cause lifespan to increase.
In fact, everything the article claims is true if the scenario you described is real.
You're thinking about direct causation which is hard to define. If running increases heart health which increases lifespan... which caused lifespan to increase? Heart health or running? The most elegant definition is to say both do. But then again being born is causative to increased lifespan as well but making a statement saying birth causes increased lifespan isn't a meaningful statement.
The nature of causation is a chain of events leading all the way back to the beginning of time. All events in that chain caused the most recent event in the chain. Reality is, in fact, made up of single tree of causative events and multiple linked chains, where ancestors in the tree are said to be causative.
Sibling nodes and events that don't have an ancestor relationship at best can only share a correlation (aka common ancestor).
