Cyberflunk

Murderbot does not approve.

Welcome to January. I thought something new happened

Sure, when reality is sane. Not with Shitler at the helm.

Burn them all

I feel like everyone just scrapes audible for metadata. I’ve searched for this mythological database for a while, and have had to settle with audible myself.

So the new RuneScape was just a cash grab? “reduce complexity “ by reducing headcount just means management incompetence, it also doesn’t make you more agile, proper guidance makes you more agile.

This is a load of shit.

They try to tell me that I have to control my reactions when I respond. It’s hard for me.

I apologize for my intensity. Sometime I see connections that are clearly self deterministic.

✌️

Fun fact: Trump is 100% a facist fuck, which is who I was referring to. He’s a self enriching oligarch wanna be who is literally killing people.

GOP sucks Trump ass on the reg. GOP is not only complicit, they enable, and support authoritarianism and anti freedom patterns.

Get your head in the fucking game if you’re correcting people.

PEOPLE ARE DYING NOW

Andy Yen tipped his hand, he’s a trumpbitch. Money you pay them supports a facist fuck

https://changelog.complete.org/archives/10783-nncpnet-can-optionally-exchange-internet-email

Be the change

Fucking cunts.

What are you talking about? RAG is a method you use. It only has limitations you design. Your datastore can be whatever you want it to be. The llm performs a tool use YOU define. RAG isn't one thing. You can build a rag system out of flat files or a huge vector datastore. You determine how much data is returned to the context window. Python and chromadb easily scales to gigabytes, on consumer hardware, completely suitable for local rag.

2nd term same as the 1st.