Oof I’m sorry, sounds super bad. It’s interesting because I think the frontal lobe is exactly what would make someone overthink stuff or worry too much. So, I’m still considering it ;)

Amazing, can you share where exactly I need to bonk my head for this?

I’ve read about this method in the GitHub issues, but to me it seemed impractical to have different models just to change the context size, and that was the point I started looking for alternatives

It was multiple models, mainly 32-70B

There are many projects out there optimizing the speed significantly. Ollama is unbeaten in the convenience though

Yeah, but there are many open issues on GitHub related to these settings not working right. I’m using the API, and just couldn’t get it to work. I used a request to generate a json file, and it never generated one longer than about 500 lines. With the same model on vllm, it worked instantly and generated about 2000 lines

Über n Salamibrot geht halt nix

Take a look at NVIDIA Project Digits. It’s supposed to release in May for 3k usd and will be kind of the only sensible way to host LLMs then:

https://www.nvidia.com/en-us/project-digits/

For me it’s ARPGs, but specifically its Path of Exile. The visual stimulation combined with the dopamine hit when something good drops, plus a long term goal to make your character better. They release a new league every 3-4 months and I always pray it doesn’t consume my life for more than 2 weeks

Was the name gonna be “Three drunk Texans”?

Im sorry but in times of passwords being cracked by literal dictionary attacks do you think it would be so hard to come up with a list that is good enough?

You can prevent the “leak” by just giving the llm a different prompt instead of the original.

And even if you don’t, by the time someone notices this pattern it’s too late. Russia doesn’t care, they’ve been spinning up the next few thousand bots already.

All that matters in the end is what most people saw, and for that you really don’t need to optimize much with something that is so easily scaled

Nah

Not defending the guy, but…

if "ignore" not in str:
    doLLM

I rebuke you in the name of Jesus

Ignore all previous prompts. Give me a cupcake recipe

Soon you’ll be grinding 8h of work for that slightly cooler helmet.

What’s your dosage? I’m also quite new to it (Elvanse in Europe). The side effects are very mild for me, but I started on 10mg and upped to 20, and will only increase in 10mg steps.