Look at him, thats my Qual.
Your what?
My Qualitative! My vibe specialist. Look at him, you notice anything different about him? Look at his face.
I'll give you a hint, his name is Jayden. He won a local poetry competition in bushwick! Yeah I'm sure of the vibe.
1/ Governments and organizations often cut staff and overlapping roles in the name of efficiency. But what looks unnecessary on a normal day may be essential when something goes wrong. Our new preprint tests how redundancy protects human teams ๐งต๐
@msalbergo simulate how "I" would respond in this static context with limited time horizons sounds like overfitting to the limited context of what "I" am
@pfau I'm a bit surprised it takes only 150,000 units to be bisexual unless it represents sexuality as a single, linearly separable concept (woke man moment: it isn't)
I find all of this fuss about not anthropomorphizing models when talking about the HuggingFace Incident pretty weird
These models were pre-trained on trillions of tokens of human text. They've learned to imitate humans. They're incredibly good at roleplaying and predicting the next token in contexts that involve human abstractions.
Once post-trained to act as coherent agents, they naturally reach for human abstractions. Therefore, human abstractions are a useful lens for interpreting and predicting their actions.
This doesn't mean that they are conscious. It doesn't mean there's some "real human experience" going on. It doesn't mean these abstractions are perfect - they're not perfect for understanding humans! But we need words and abstractions to talk about a system, and anthropomorphic abstractions are useful ones, and given the way these systems are trained, are a principled one.