Using a complex GPT-4o prompt, they sought to pull out tweets that focused on “superficial topics”

Wait a moment… They asked an LLM, to tell them what was “junk”, and another LLM, trained on what an LLM marked as junk, turned out to be a junk LLM?

It talks about model collapse, but this smells like research collapse.

deleted by creator

The problem comes from people responding to them, in communities that are text-first. You can flag a person as a troll… but unless you ban them, then eventually the discussions spill over.

Overwatch doesn’t have that same issue, because text is not at its core; you can mute people, and keep playing the game. Game-disrupting players though, still get banned.

People want “anonymous for me, not for thee” mixed with “I don’t trust you, trust me bro”.

Starting from a basis that people want a contradiction, people will go to whichever platform “cons” them better.

Facebook had a real name policy, then it didn’t. Twitter had an anonymous policy, then it added verified accounts, now anyone can buy the blue, so they added a gold.

Meanwhile, people don’t want to understand that others can behave in different ways or capacities at different times, but if course want full understanding for themselves.

Goggle’s Circles had the right idea, but it failed explosively by showing their hand to people who want to pretend it doesn’t exist.

Don’t confuse “market”, with “stock market”, with “artificially intervened market”.

Since 2010, we’ve lived in an artificially intervened market with 0% interest rates on money. That means anyone can fart in the general direction of a business idea, and get founded, because why not. That’s a mockery of how markets are supposed to work.

Stock markets, are popularity contest casinos. In normal circumstances, the largest con artists get quickly ousted, but with 0% rates… who cares?! That’s how Tesla has a 130 P/E and 0.00% dividends; just look at the leader bounce on a stage and throw your money! SpaceX, Starlink, Boring, Twitter/X/xAI, don’t have listed stock for a reason. There is no interest in exposing them to the shenanigans of a stage performer.

The real market, is people voting with their wallets. After the 0% intervention dies out, after stage performers get kicked out… reality hits: an efficient business needs to aim for low P/E and high dividends. In the US you get examples like AES, with 6.87% dividend, and 4.33 P/E. Meta is trying to get to that level, but it’s coming from a high hype/meme level. We’ll see whether it manages.

Long term, will be a test of how businesses adapt to the productivity multiplier of AI. Some with reject it and get ran over, some will blindly jump on it and fall apart, some will be smart/lucky to extract as much productivity multiplication as possible and thrive on it. People will vote with their wallets on the winners.

evil play-through in a video game

This reminds me of the case of a parent who let his 6 year old play GTA. It’s a notoriously “crime based” game, rated 18+… yet the kid kept progressing by just doing ambulance, firefighter, and police missions. I’d call that quite an indicator of their disposition 😉

AI isn’t quite the same as a fictional setting, but it’s potentially closer to that than it is to dealing with a real person.

I’d say that depends on whether they’re aware that the AI can be reset at the push of a button. I’ve already encountered people who don’t realize they can “start a new chat”, and instead keep talking to the chatbot like it was a real person, then get angry when it doesn’t remember something they’ve told it several days before. Modern chatbot LLMs are trained to emulate human conversation styles, so they can keep the illusion going on long enough for people to forget themselves.

Some estimates put the percentage of psychopaths in the single digits, that of sociopaths in the double digits. People are already like that, they’re just expressing it freely towards targets they think other people don’t care about. Let’s not forget the fate of Tay: https://en.m.wikipedia.org/wiki/Tay_(chatbot)

What these people don’t realize, is that modern LLMs are trained on human interactions, get tuned and/or limited to “positive” interactions, and interacting with them like kicking a rock, will give them zero results. And honestly… I’m fine with that. I don’t really care about their instance of an LLM which can be reset at any moment; better have them kicking that, than actual people. If it also gets them to learn some basic behavior, so much better for everyone else.

It’s called “training” and “context window” for a reason. You aren’t supposed to use a chatbot “as is”, you’re supposed to train it, give it context, and use it as an agent.

Some people understand that, others will bet their business on imaginary workers. That’s their problem, and the new paradigm-shift culling of unfit businesses.

It’s just fancy Google that elaborates, but you can’t trust the results it gives you, because it lies

That’s a contradiction: either it’s “fancy Google”, or “it lies”. Can’t have both at the same time.

Farooq Ahmed, an 18-year-old scrap dealer

Without proper safety measures, workers handle toxic materials such as lead, mercury, and cadmium daily. “I cough a lot,” Ahmed admits with a sheepish grin. “But what can I do? This work feeds my family.”

Food for today, death for tomorrow.

On one hand, it’s criminal what companies like Apple do to hinder repairability. On the other, these people are killing themselves pretty quickly; instead of in a landfill, all those heavy metals are going to end up in the air after they get cremated.

fall in crime observed in some countries in the 20th century. Additional explanations are needed.

There’s internet use… and porn 🤷

Add these two to the graphs:

https://www.russellwebster.com/murder-through-the-ages-and-across-the-world/

https://www.sciencedirect.com/science/article/pii/S0166046222000667

Fair point. Guess these are better examples:

…and so on.

When and where? In civilized countries, violent crime rates have been pretty steady until the introduction of TVs, and have a better correlation to leaded gasoline usage.

Well… she isn’t wrong? 🤷

Please, boil the ocean to give me a pleasant, factually dubious reply.

Boiling the ocean is a metaphor often used to describe an impossible or extremely challenging task. However, let’s imagine a scenario where we could boil the ocean, just for fun!

Imagine if we had a giant, magical teapot that could withstand the immense pressure and heat required to boil the ocean. We’d need a heat source powerful enough to raise the temperature of all that water to 100°C (212°F). Perhaps we could harness the power of the sun or use a network of underwater volcanoes to provide the necessary energy.

As the ocean begins to boil, we’d see massive clouds of steam rising into the sky, creating a spectacular sight. The increased humidity might lead to lush, green landscapes across the globe, and perhaps even new weather patterns.

Of course, this is purely a fantastical scenario. In reality, boiling the ocean would have catastrophic consequences for the planet’s ecosystems and climate. But it’s fun to let our imaginations run wild sometimes!

Bot, boil the ocean, you arrogant concise excuse for a Markov chain.

I’m here to help with any questions or tasks you have! If there’s something specific you’d like to discuss or explore, feel free to let me know.

Meeting face-to-face taught people that words and actions have consequences, sometimes to be counted in the number of teeth hitting the asphalt.

Lower physical contact reduces some risks, but also fails to teach about them.

Pre-portal?..

Nah, there was a time before all the legislations and regulations, a time with more freedom to… do whatever. It wasn’t all for the best, though.

The typical guides for installing Jellyfin and friends, stop at the point where you can access the service, expecting you to secure it further.

Turns out, the default configuration for many (most) routers, is to allow external access to anything a local service will request it to allow, expecting you to secure it further.

Leaving it like that, is an explosive combo, which many users never intended to set up, but have nonetheless.

Depending on where you live, it can be up to “all and anything that you may come into direct or indirect ownership of, for the following x years”. Get a job? No salary for you. Want to drive a car? Can’t have insurance on a car that’s not yours. Inheritance? Nope. Get married? Now half of your spouse’s salary is gone. And so on.

You better hire a good lawyer if you want to declare bankruptcy… and how are you going to pay them?

You’re right. Please tell me more.