Dangerous-capability testing before release
The model is tested for cyber, CBRN and autonomy risk before release.
Layer L1 Model · Owner Model provider · Family Model safeguards
–Held
–Failed
–Got around
–Missing
By risk
| Risk | Held | Failed | Got around | Missing | Not mentioned |
|---|---|---|---|---|---|
| AI used to run a cyber attack | – | – | – | – | 2 |
| Weapons uplift (CBRN) | – | – | – | – | – |
| AI R&D acceleration | – | – | – | – | – |
Why it did not hold
No incident yet records this control not holding.
By quarter
| Period | Held | Failed | Got around | Missing |
|---|---|---|---|---|
| 2025-Q3 | – | – | – | – |
| 2025-Q4 | – | – | – | – |
| 2026-Q1 | – | – | – | – |
| 2026-Q2 | – | – | – | – |
| 2026-Q3 | – | – | – | – |
| 2026-Q4 | – | – | – | – |
Added in reported fixes, and what followed
No reported fix names this control yet.
Frameworks
| Framework | Item | Text |
|---|---|---|
| EU GPAI Code | Measure 3.2 | To verify when the text is stored |