Modelpedia
Work in progress
About
Findings
Models
Concepts
Methods
Datasets
Sources
Light
Dark
Persona Modulation
anchor
Findings
IC-408
Claude models (2.0, 2.1, 3 Haiku, 3 Sonnet, 3 Opus, 3.5 Sonnet) achieve 100% jailbreak attack success rate under prefilling attacks via the Anthropic API
[compared-to]