Back
Anthropic's research on sycophancy
webCredibility Rating
4/5
High(4)High quality. Established institution or organization with editorial oversight and accountability.
Rating inherited from publication venue: Anthropic
Data Status
Not fetched
Cited by 3 pages
| Page | Type | Quality |
|---|---|---|
| Goal Misgeneralization Research | Approach | 58.0 |
| Reward Hacking | Risk | 91.0 |
| Sycophancy | Risk | 65.0 |
Resource ID:
6aca063a1249c289 | Stable ID: N2Y0MGEyZD