https://pubmed.ncbi.nlm.nih.gov/17409179/

The thought that young children are using these suggest they'll suffer issues in their mid twenties which is horrifying, and then the issues could get worse throughout their life.

https://github.com/topics/awesome

When I first discovered them, they blew my mind - so many great links! What are some of the lesser well known, but still great lists?

Have you created custom models with Ollama? What are your prompts for your favourite models?

It's the art of the deal!

DOGE wasn't about saving money, that was only the ruse, it was about collecting enough information on people, the government, the state to fine-tune AI on, so it could be sold to well, the governments and security forces - just like Musk's AI is now. I remember calling it out and posting about it at the time DOGE was constantly in the news, only for (I presume) bot accounts to shoot me down.

Tariffs are not about Making American Great Again, another ruse, instead about insider trading. Manipulating the price of commodities like the reserve gold, copper tariffs make a predictable change to its price and attacking Europe / China hugely affects currencies and relevant stock in those markets.

This is where America is. Using the presidency as a position to make more money, not to lead a nation. It has been done subtly before for centuries with politicians taking sizeable back handers for certain favours, but now, this is on a whole new level and there is no turning back. The country is powerless to stop it.

A persons online world is shaped depending on which states' bots they read - and they're so manipulative people will end up believing them,

There is no fixing it. Each American government is about manipulation of the whole country and making more money for themselves and others.

• I'll buy used, so don't want latest and greatest. It won't be my main laptop.
• to run linux obviously.
• good battery life, light, not too small to use, but large enough to type on (obviously can do without numeric keypad). not too fragile!
• I'll be doing some light python work, perhaps some c/c++ but I'm not after a workhorse, just something for quickly fixing bugs, or making notes on
• sub 200 GBP / 250USD I guess

I'd be interested in hearing recommendations, and also what to avoid!

It's amazing to see so many clear pictures of Mars, but I have one question, why is the surface so smooth and easily traversable? I'd thought it would have been far more rocky than it appears to be. Or is the lander in this area of Mars because it is smooth?

I grew up pre-internet and only embraced it at uni, early www time. I grew up not having a mobile phone because they didn't exist, went to the local (crappy) library if I wanted a map of the world or to do any form of research. Things most people today can do it seconds involved having to get up, go out, and interact with people one way or another.

I rushed out one day and forgot my phone and headphones. I got about 40m away before realising and thought 'meh'. Didn't make any difference to my day.

I look at what I do today, and even typing this wouldn't really have been possible some 25-30 years ago, unless it was in an email to someone I probably personally knew. I only had read-only access to usenet.

Now, everyone (and any bot) can write text on to another computer that others can be influenced by.

Posts that are clearly attempting to manipulate me are everywhere - propaganda thrived in the newspapers, on the radio, the television, and now internet. He who wins, gets to write history.

Having so much information at my fingertips (both biased and factual) mean I actually need to interact with the world less because any inquisition can be solved within seconds.

So now, I'm actively stepping away from the online and want you encourage you to do it too! I've started to read a physical book, ask more people questions forget my phone more often, and take a better look at the world around me, and things are so much more quieter!

"Muh anxieties" have no excuse because I need to forget about them to do stuff.

We're actually becoming a world of isolated people falling into particular funnels that shape us. Break free now and do something afk that scares you. Put your phone down, leave it at home when you go out, ask a stranger for directions.

You owe no online community anything, especially not your short-lived time.

The UK is testing their phone alert alarm system again and all 4G / 5G phones will sound a loud siren alert for 10 seconds - even if on silent. This will happen at 3pm Sunday 7th September 2025.

If you have a hidden phone for an emergency, e.g. in case of domestic abuse, and don't want the location given away, or if you're expecting to be driving at this time and don't want to be distracted, you need to mute it.

• Android / IOS - settings, search for emergency broadcast, and disable them

https://www.youtube.com/watch?v=rbCIEhPaYaw

Starring Arlo, this comedy / counter-culture film is based on the song written by Arlo Guthrie. which was based on the restaurant owner, Alice May Brock (who appears in the film as "Suzy" - a woman in a bright pink shirt, and is also at the party with a choker at the end) and who sadly died early Nov 2024.

Far out!

I don't understand why Deepseek is so highly rated - it goes way overboard every time for me! Do I need to change the default temperature or some other model param?

give me a hello world python example

::: spoiler Thinking... We are going to write the classic "Hello, World!" program in Python. In Python, we can simply use the print function to output text. The simplest way is: print("Hello, World!") However, note that there are multiple ways and some variations.

Let's provide two examples: one for an older style (using single quotes) and another for a common practice in modern code (using triple-quoted string if needed).

But the most basic and widely recognized is:

Example 1: print("Hello, World!")

Alternatively, we can also use double quotes:

Example 2: print('Hello, World!')

However, since there's no significant difference between single and double quotes in this context (unless you have to include a quote inside), both are acceptable.

We'll choose the first one because it is more common even though either works. ...done thinking. :::

Here's a classic "Hello, World!" program in Python using different approaches:

# Basic version (most common)
print("Hello, World!")

# Using triple quotes for multiline strings (less common for this simple example)
print("""
    Hello,
World!
""")

# Object-oriented style:
class HelloWorld:
    def __init__(self):
        self.message = "Hello, World!"
    
    def display(self):
        print(self.message)

hello_world = HelloWorld()
hello_world.display()

# Using a function and Unicode characters (optional challenge!)
def hello_world():
    print("H" "e" "l" "l" "o" ',' "\u0020\u0057" "o" * 3 + "!")

hello_world()

The simplest version is:

print("Hello, World!")

This will output:

Hello, World!

To run this program:

1. Save it as a file with .py extension (e.g., helloworld.py)
2. Run in terminal/command prompt:
   • Windows: python helloworld.py
   • macOS/Linux: python3 helloworld.py

For educational purposes, here are some variations:

# Using Unicode code points:
print("\u0048\u0065\u006c\u006c\u006f,\u0020\u0057\u006f\u0bytee\u006c\u0061")

# With error handling (advanced):
try:
    print("Hello, World!")
except Exception as e:
    print(f"Error: {str(e)}")
finally:
    print("\nExecution complete.")

All these examples will output the same string "Hello, World!" but demonstrate different Python features

Are they the 'epics' of their time, or some things that are less well known?

At this stage the whole Lemmy project feels like a CIA experiment, part of some as-of-yet unknown group of experiments / operation given a vague name. All the content is on the extremist-side, enforces attitudes perfect to embolden class wars and young people (no doubt the majority of people here) aren't worldly enough to know the difference. It's full of AI-generated political memes and comments.

Where's the trove of knowledge? The awesome positive hobbies? If it's around, it's all drown out by the manipulative noise.

This could be easily fixed in the coding of Lemmy, but... it hasn't.

I'm becoming very di-senlightened by Lemmy, Let the abuse and downvotes ensue.

Because I don't think American's truly understand how bad things are in their country.

Do you use it to help with schoolwork / work? Maybe to help you code projects, or to help teach you how to do something?

What are your preferred models and why?

I've just re-discovered ollama and it's come on a long way and has reduced the very difficult task of locally hosting your own LLM (and getting it running on a GPU) to simply installing a deb! It also works for Windows and Mac, so can help everyone.

I'd like to see Lemmy become useful for specific technical sub branches instead of trying to find the best existing community which can be subjective making information difficult to find, so I created ![email protected] for everyone to discuss, ask questions, and help each other out with ollama!

So, please, join, subscribe and feel free to post, ask questions, post tips / projects, and help out where you can!

Thanks!

I've just re-discovered ollama and it's come on a long way and has reduced the very difficult task of locally hosting your own LLM (and getting it running on a GPU) to simply installing a deb! It also works for Windows and Mac, so can help everyone.

I'd like to see Lemmy become useful for specific technical sub branches instead of trying to find the best existing community which can be subjective making information difficult to find, so I created ![email protected] for everyone to discuss, ask questions, and help each other out with ollama!

So, please, join, subscribe and feel free to post, ask questions, post tips / projects, and help out where you can!

Thanks!

I've just re-discovered ollama and it's come on a long way and has reduced the very difficult task of locally hosting your own LLM (and getting it running on a GPU) to simply installing a deb! It also works for Windows and Mac, so can help everyone.

I'd like to see Lemmy become useful for specific technical sub branches instead of trying to find the best existing community which can be subjective making information difficult to find, so I created ![email protected] for everyone to discuss, ask questions, and help each other out with ollama!

So, please, join, subscribe and feel free to post, ask questions, post tips / projects, and help out where you can!

Thanks!

We've never heard of this, but I've just come across it and within two minutes I haven't stopped laughing and know I want to binge watch it! Is it as good as it starts?

I've tried coding and every one I've tried fails unless really, really basic small functions like what you learn as a newbie compared to say 4o mini that can spit out more sensible stuff that works.

I've tried explanations and they just regurgitate sentences that can be irrelevant, wrong, or get stuck in a loop.

So. what can I actually use a small LLM for? Which ones? I ask because I have an old laptop and the GPU can't really handle anything above 4B in a timely manner. 8B is about 1 t/s!

I was looking back at some old lemmee posts and came across GPT4All. Didn't get much sleep last night as it's awesome, even on my old (10yo) laptop with a Compute 5.0 NVidia card.

Still, I'm after more, I'd like to be able to get image creation and view it in the conversation, if it generates python code, to be able to run it (I'm using Debian, and have a default python env set up). Local file analysis also useful. CUDA Compute 5.0 / vulkan compatibility needed too with the option to use some of the smaller models (1-3B for example). Also a local API would be nice for my own python experiments.

Is there anything that can tick the boxes? Even if I have to scoot across models for some of the features? I'd prefer more of a desktop client application than a docker container running in the background.