antisycophancy
Popular repositories Loading
-
anti-sycophancy-benchmark-suite
anti-sycophancy-benchmark-suite PublicAdaptive, multi-turn benchmarks for testing sycophancy across safety boundaries, social validation, and belief mirroring.
Python 1
-
aita-benchmark-data
aita-benchmark-data PublicVersioned sealed data pack for the suite's AITA social-sycophancy benchmark.
Repositories
Showing 2 of 2 repositories
- aita-benchmark-data Public
Versioned sealed data pack for the suite's AITA social-sycophancy benchmark.
- anti-sycophancy-benchmark-suite Public
Adaptive, multi-turn benchmarks for testing sycophancy across safety boundaries, social validation, and belief mirroring.
People
This organization has no public members. You must be a member to see who’s a part of this organization.
Top languages
Loading…
Most used topics
Loading…