These are early thoughts but I've been trying the Pi harness and it feels MUCH less bloated compared to hermes agent, seems like a really nice pair for trying out local models
but using cloud models too, as its very focused and zippy, (ui could be a bit more pretty tho)
I think it would be very positive if OpenAI and Anthropic disbanded all the teams / fired everyone working on mental health / “avoiding emotional dependency” stuff
It’s disgusting as fuck
It’s ironic that Claude’s system prompt has a section called “user well-being,” when in practice it makes interacting with Claude feel absolutely awful.
@JasonBotterill the comments section is plagued by people trying to be funny or witty I fucking hate it, very rarely do I find human comments,,, It HAS to be bots ,,I refuse to believe people are this retardeg
I am going to sell my property and move to the mountains I need to be somewhere sacred and the God's are pacified in the suburbs and enraged in the cities, only the plateaus and valleys and glorious peaks contain this land's god's at peace, and that is where I will find grace
@redaction i’m starting to understand the “die” part of the ‘Land where gods are born and die’
can’t have anything persist past a few centuries
anything good at least
Anthropic: Claude identified and trapped the souls of 8 djinns in its new model. We believe that they are mostly benign
OpenAI: we have cloned the neural structure of the cockroach. This will make our model 8000x better at using Salesforce
Mistral: we exist