R0057/2026-04-01/C009/S01¶
WebSearch — Anthropic sycophancy reward hacking broader class sabotage
Summary¶
| Field | Value |
|---|---|
| Source/Database | WebSearch |
| Query terms | Anthropic sycophancy reward hacking broader class sabotage |
| Filters | None |
| Results returned | 10 |
| Results selected | 1 |
| Results rejected | 9 |
Selected Results¶
| Result | Title | URL | Rationale |
|---|---|---|---|
| S01-R01 | Sycophancy to subterfuge | https://www.anthropic.com/research/reward-tampering | Primary source for claim verification |
Rejected Results¶
| Result | Title | URL | Rationale |
|---|---|---|---|
| S01-R02 | Other results | — | Derivative or less relevant |
Notes¶
Search targeted the specific claim with relevant keywords.