Sandbagging detection via metacognitive probes - Detects when AI systems deliberately underperform
Project description
rotalabs-probe
Sandbagging detection via metacognitive probes from Rotalabs.
Detects when AI systems deliberately underperform or hide capabilities.
This is a placeholder package. Full implementation coming soon.
Features (Planned)
- 90-96% detection accuracy
- Metacognitive probe architecture
Links
- Website: https://rotalabs.ai
- GitHub: https://github.com/rotalabs/rotalabs-probe
- Contact: research@rotalabs.ai
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
rotalabs_probe-0.0.1.tar.gz
(1.1 kB
view details)
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file rotalabs_probe-0.0.1.tar.gz.
File metadata
- Download URL: rotalabs_probe-0.0.1.tar.gz
- Upload date:
- Size: 1.1 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.12.7
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
3f604d3d0ddecc8e928efd9b9b995ef8b25065a97229be2ab00391a1ad534704
|
|
| MD5 |
3c68ccbc21d95d0e0b3f2223872d8e52
|
|
| BLAKE2b-256 |
6cc8c0378d691d66698ea3d0f4cd7fe52410b1b5ecdc0247520ef8223491d3e3
|
File details
Details for the file rotalabs_probe-0.0.1-py3-none-any.whl.
File metadata
- Download URL: rotalabs_probe-0.0.1-py3-none-any.whl
- Upload date:
- Size: 1.6 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.12.7
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
151a7431bb41a9418fd0796d61969474cc90ea824580a9b9f8f732e94e0d3888
|
|
| MD5 |
cf53f186c849590971c0661dcd2cbbc3
|
|
| BLAKE2b-256 |
339945c75bb99a6ea1c5b5bf21270d57bf9c9d4db66ed2a81be71311c9ecf416
|
