Google Study: Chatbots Using Companion Language Like "I'm Worried About You" Feel Less Trustworthy
jacyanthis · x · 2026-09-03
A new simulation study from Google Research spanning users in the US, UK, India, and Nigeria finds that when chatbots use anthropomorphic companion language ("I'm worried about you", "You are great, dear"), people rate them as less likable, humanlike, and trustworthy.
Related event: Google study: anthropomorphic chatbot language backfires with users(4 posts)→
More from Research
- SPAR to run RCTs testing whether secretly misaligned AI can sabotage human decisions — austinc3301 · 2026-09-03
- Materials scientist flags DiffCrysGen outputs violating charge neutrality, calls out garbage-rate reporting gap — CatAstro_Piyush · 2026-09-03
- Dynamical systems view of motor cortex: preparatory activity holds movement-specific code — burny_tech · 2026-09-03
- EleutherAI paper: persistent agent memory can enable 'authorization laundering' attacks — EleutherAI · 2026-09-03
- RealSWE benchmark: realistic user requests test coding agents, explicit intent boosts results — skku · 2026-09-03
- How Artificial Analysis builds its coding agent index: 3 benchmarks, cost and time — ArtificialAnlys · 2026-09-03