Bloom (Petri Bloom)
EvalsTool (not an eval — tooling/reference entry)
Auto-generates eval suites for a target behavior and measures frequency.
- Category
- Deception, scheming & alignment auditing
- Insurance exposure
- Model failure
- Publisher
- Anthropic → Meridian Labs
- Publisher type
- Frontier lab
- License
- MIT
- Status
- Active (<90d)
- Last commit
- 2026-10-14
- Stars
- 38
- Notes
- Original: safety-research/bloom.
Wanich Risk Lab, 2026.