promethean@quantizor3h> OpenAI and Anthropic researchers independently reached similar conclusions about preserving CoT monitorability. Good.OrcaRouter 🐳@OrcaRouter12hRumor is next-gen models at OpenAI + Anthropic are showing emergent misalignment beyond what’s been publicly reported. Technical backgrounds sound particularly interesting: → Misaligned behavior appearing in CoT → Existing monitors reportedly have insufficient AUROC → Show more40
OrcaRouter 🐳@OrcaRouter12hRumor is next-gen models at OpenAI + Anthropic are showing emergent misalignment beyond what’s been publicly reported. Technical backgrounds sound particularly interesting: → Misaligned behavior appearing in CoT → Existing monitors reportedly have insufficient AUROC → Show more
promethean@quantizor8hThis has to be a Black Mirror viral ad right? ollobot.comOllobot - A Brand New Cyber PetDiscover OLLO, a new kind of robot pet for cyber living—designed to connect hearts, share moments, and feel at home with your family.39
