Alignment Faking (open replication)

Framework / harness (not an eval — tooling/reference entry)

Replication of alignment-faking experiments.

Category

Deception, scheming & alignment auditing

Insurance exposure

Model failure

Publisher

Anthropic

Publisher type

Frontier lab

License

MIT

Status

Stale (>12mo)

Last commit

2025-04-04

Stars

60

View source on GitHub →

Wanich Risk Lab, 2026.