Gleipnir Prompt Injection Monitoring Collection Injection augmentation, hard-label mixtures, census filtering, behavior-grounded prompts, and original 4B/9B monitoring baselines. • 10 items • Updated 8 days ago
Gleipnir Prompt Injection Monitoring Collection Injection augmentation, hard-label mixtures, census filtering, behavior-grounded prompts, and original 4B/9B monitoring baselines. • 10 items • Updated 8 days ago