Hume builds safety framework from scratch for human-like user simulator models

LukeW · x · 2026-11-21

Hume's new user simulator model can sound like real people—which also means it could deceive them via fake reviews, scams, or impersonation. With few established safety practices for user models on a public API, the team built a safeguard framework from scratch: each message is checked in context and screened across sessions. The team also established a safety testbed for user simulators. The hard part: behaviors undesirable in standard assistants, like manipulation and harassment, are real human behaviors that must be modeled in some contexts, requiring an entirely new restrictive framework.

Original post →

More from Models

Models channel →