Prosaic IntelligenceResearch
Research on consumer AI safety, including the development of benchmarks to assess risks not adequately captured by existing evaluations.
AI political spectrum
We tested where 20 popular AI models lie on the two-dimensional political spectrum — they all landed in the libertarian left.
Topology-Conditioned Backdoors
The behavior we observe during evaluations and benchmarks may be different than the behavior we observe in deployment.
All research
- AI political spectrum
We tested where 20 popular AI models lie on the two-dimensional political spectrum — they all landed in the libertarian left.
- Topology-Conditioned Backdoors
The behavior we observe during evaluations and benchmarks may be different than the behavior we observe in deployment.