Your point is taken, and I didn’t mean to sound like I was implying that the world == US. I would, however, mention that Trump is on the world stage, and he is engaging other leaders with all kinds of stupidity. Threatening allies while giving hand jobs to despots. The world is getting infected just by having to deal with him.

That being said, you are right to point out that there are probably some Albanian sheep farms where sanity yet prevails.

Is that a photo of him trying to shake hands with a mirror?

I think we’ve entered a stage of humanity where, “just think about this for a second and you’ll realize this is far too stupid to be true,” just isn’t a thing any more. I’m not saying he wrote the note. I’m not saying anything about Epstein’s death at all. Just that the world has become so absurd that there is no bottom to the stupidity.

It’s okay. They’ll probably steal whatever you put in it anyway. Imagine if the Trumps make a big stock move and then had everyone’s “Trump account” cover the bet at a tidy profit.

Trump has tainted this entire country with this stank. The businesses paying him off. The people licking his crack. The politicians giving him cover. Fuck all of them. Forever.

We (my company) are trying to create agents that read a story and translate that into prompts, then execute said prompts, then review the output. The only piece missing is accepting the merge.

I’m not anti-AI, but a human needs to be involved at every step because a minor mistake made at the first step will amplify through the agentic pipeline.

A human should review every single thing that comes out of AI — especially if it is to be fed back into AI.

https://lemmy.zip/comment/26338870

You’d just be paying it forward. Ten minutes after you watch some girl’s roommate jilling off, she’s watching you crank your meat handle.

It’s a MacBook Pro. 36GB of ram. I am sure Macs have some kind of gpu and I understand it somehow combines GPU ram with system ram, but I don’t really know Mac hardware very well.

It’s beefy for a laptop, but the desktop I built for myself several years ago had 32 GB of ram and a GTX 1660, so I’m guessing they are similar in capability. I gave that to my daughter, so I can’t run a comparison right now.

EDIT: After doing just a bit of research, I’ve learned the unified memory architecture that Macs use, while not ideal for many purposes, is actually a big advantage for running larger inference models. So it’s possible that this particular model wouldn’t run at all on my Linux box or would run much slower because the full model wouldn’t fit in the 6GB of VRAM and create a lot of memory thrashing.

Small models are improving and becoming more capable. The quality of local LLMs is basically unbounded. The context size of local LLMs is bounded by hardware. So local LLMs can be very capable for small, self-contained tasks.

qwen 3.6 35b running locally:

Write a Python script that can pull weather data from public sources and provide the high and low temperature for the current day in Miami, FL.

Single shot. No tool/internet use, so it didn’t pull this script from elsewhere.

import requests

def get_miami_weather():
    # Miami, FL coordinates
    LATITUDE = 25.7617
    LONGITUDE = -80.1918

    # Open-Meteo API URL (free, no API key required)
    url = (
        f"https://api.open-meteo.com/v1/forecast?"
        f"latitude={LATITUDE}&longitude={LONGITUDE}"
        f"&daily=temperature_2m_max,temperature_2m_min"
        f"&timezone=auto"
    )

    try:
        response = requests.get(url, timeout=10)
        response.raise_for_status()  # Raises error for 4xx/5xx HTTP status codes
        data = response.json()

        # Index 0 corresponds to the current day
        high_c = data["daily"]["temperature_2m_max"][0]
        low_c = data["daily"]["temperature_2m_min"][0]

        # Convert to Fahrenheit (commonly used in the US)
        high_f = (high_c * 9/5) + 32
        low_f = (low_c * 9/5) + 32

        print("🌤️  Miami, FL Weather for Today:")
        print(f"High: {high_f:.1f}°F ({high_c:.1f}°C)")
        print(f"Low:  {low_f:.1f}°F ({low_c:.1f}°C)")

    except requests.exceptions.HTTPError as http_err:
        print(f"❌ HTTP error occurred: {http_err}")
    except requests.exceptions.ConnectionError:
        print("❌ Error: Could not connect to the weather API.")
    except requests.exceptions.Timeout:
        print("❌ Error: Request timed out.")
    except requests.exceptions.RequestException as err:
        print(f"❌ An error occurred: {err}")
    except KeyError as key_err:
        print(f"❌ Error parsing data: Missing expected key {key_err}")
    except Exception as err:
        print(f"❌ Unexpected error: {err}")

if __name__ == "__main__":
    get_miami_weather()

Output:

% python3 ./m_weather.py
🌤️  Miami, FL Weather for Today:
High: 88.0°F (31.1°C)
Low:  73.2°F (22.9°C)

I tried to keep the size and scope within something that would reasonably fit in a comment. Looks pretty decent to me, but I can’t write Python myself. Never learned. I double-checked the LAT & LON of Miami, and it’s spot on.

It did take 47 seconds, while a cloud LLM would probably take 5 or less.

All I’m saying is local LLM isn’t garbage and it is getting better all the time.

I wouldn’t count on anything. The only winner in infighting is the status quo. There’s a larger lesson there, should any anti-progressive Dems care to look for it.

😑

It’s like he’s trying to smile but has forgotten the muscle movements required to make it happen.

Agreed. We’ve had multiple wake-up calls that we don’t have any guardrails against an unstable President, and we’ve done nothing about it. I mean technically we have guardrails. But the reality is our elected officials are a bunch of feckless cowards who value being in power more than they value wielding it responsibly. And since impeaching a President is tantamount to a nuclear bomb enema, politically speaking, no one is willing.

We are electing the fundamentally wrong sorts of people. It’s not just age.

Exactly.

Claude: