We killed Henry Kissinger.
LangleyDominos
joined 2 weeks ago
Given the way LLMs function, the will have a hard time with therapy. Chat GPT's context window is 128k tokens. As you chat, your prompts/replies add up and start filling the context window. GPT also has to look at its own responses for context. That fills up the window as well. LLMs suck with nearly empty context windows and nearly full context windows. When you're close to having a full context window, it will start hallucinating and having problems with responses. Eventually it will only be able to focus on parts of your conversations because you've blown past the 128k token mark.
The ways to mitigate this problem have to be done by the user and they disrupt therapy.
Niacin rush. He downed 6 sausages in the green room.
Trump 2016 - Make America Great Again, Biden 2020 - Build Back Better, Trump 2020 - BBB - Big Beautiful Bill that will Make America Great Again Again.
They're just going to keep bouncing this same nationalist sentiment back and forth until someone notices that nothing is happening.
My takeaway: whales need video games
A monument of flesh, coated in ochre and topped with brass wool.
It's just a new version of "literally me"
It's adapting a cool persona from a movie, TV, or game character. Ryan Gosling in Drive is literally me, you would watch Drive to aura farm.
Yeoman dream.
A large part of posting is to just read the thread title, or skim the first sentence of a post, and then reply with your thoughts. We kind of kid ourselves that posting is social interaction. It's mainly isolated reaction.
This is why he wasn't allowed on the door.
This article is evidence of them looking busy.
You'll never take me alive you robotic sombitches.