game theory fix for lack of willpower:
eliminate choice entirely.
hernán cortés burned his ships so his troops couldn't retreat.
you don't need more discipline. you need a commitment device, a constraint that makes backing out mathematically impossible.
Being a dad is insane because you will literally close your eyes and see your son’s smiling face radiating more beauty than you thought the whole universe could hold
@callmelastborn1@Naturalphilosy He probably chose to say it shortly for dramatic effect. I think he is talking about the desire to be understood, not the state of it.
'Traits I value: responsive, alive, generous, considerate, original, sensitive, brave'
from Susan Sontag 'As Consciousness Is Harnessed to Flesh: Journals and Notebooks, 1964-1980'
Super interesting and highly promising technique for interpretability by Anthropic! The J-lens seems likely to become a tool in stock for any good interpretability toolkit. Well done! :D
Ps. it also does have a lot of conceptual bearings on the nature of access consciousness vs. phenomenal consciousness - I'll write more about this. I ofc don't think the reasoning that we're seeing a global workspace and _therefore_ the "signatures of consciousness" in these systems. But the principle that a system will only ever be able to report on part of its internal state (except in highly specific corner cases engineered to be able to report more) is very well expressed in this research. Exciting times :-)