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.
More from Models
- Google launches first interactive Gemma 4 explainer teaching how LLMs work in the browser — DynamicWebPaige · 2026-11-21
- InferenceBench recap: Anthropic led for half a year before Google's dramatic comeback — maksym_andr · 2026-11-21
- Persimmon built a safety framework from scratch for human-like user models — gharik · 2026-11-21
- Persimmon is now open to everyone, safety filters credited for the decision — gharik · 2026-11-21
- Persimmon launches pro and ultra API tiers, ends waitlist — CShorten30 · 2026-11-21
- RCTBench: Only 3 of 9 Decision Models Hit 1,000 Guests in RollerCoaster Tycoon 2 — bo_wangbo · 2026-11-21