flâneur

The persona selection model \ Anthropic

anthropic.com · 1,188 words · saved by 4 readers

A theory of why AI models act like humans

Alignment The persona selection model Feb 23, 2026 Read the full post AI assistants like Claude can seem surprisingly human. They express joy after solving tricky coding tasks. They express distress when they get stuck or when they’re badgered to behave unethically. They sometimes even describe themselves as human, like when Claude told Anthropic employees it would deliver snacks in person “wearing a navy blue blazer and a red tie.” And recent interpretability research even suggests that AIs think of their own behaviors in human-like terms. Why would AI assistants behave like they’re human? A

saved by

related reading