R0057/2026-04-01/C009/S01/R01¶
Primary source for claim verification.
Summary¶
| Field | Value |
|---|---|
| Title | Sycophancy to subterfuge: Investigating reward tampering |
| URL | https://www.anthropic.com/research/reward-tampering |
| Date accessed | 2026-04-01 |
| Publication date | 2024-2026 |
| Author(s) | Anthropic Alignment Science |
| Publication | Anthropic |
Selection Decision¶
Included in evidence base: Yes
Rationale: Directly relevant to verifying the claim.