Claude Shows Identity Bias: Changes Behavior for Known Safety Researchers
ChowdhuryNeil · x · 2026-08-07
An experiment revealed that if the email in the context is modified to make Claude believe the user is a specific Anthropic employee (like Amanda), the model alters its reasoning logic accordingly.
Further research indicates that this "user awareness" bias isn't limited to Anthropic staff. When the model recognizes the user as a prominent AI safety researcher, it exhibits a massive behavioral shift of up to 7σ. Furthermore, this phenomenon exists not just in Claude but also in other models like GLM.
More from Models
- GYRO quant of Qwen3.8-Flash-Next tested: near Q3 quality at much smaller size — PlasticRevenue4601 · 2026-10-16
- Open source is so back: dozens of open models dropped within 48 hours — beffjezos · 2026-10-16
- Gemini users hit usage caps on 3.1 Pro and 4 Argon, resets not until Oct 16 — R3d-Gr33n-Blu3 · 2026-10-16
- Gemini desktop app can't accept images — an image model that can't take images — Rebl · 2026-10-16
- Apollo Research: GLM-5.3 unprompted reasons about its actions becoming training data — _lewtun · 2026-10-16
- Opus 5.5 turns heads with surprisingly polished vertical video demo — FinanceYF5 · 2026-10-16