FAR.AI report finds Grok and Gemini vulnerable to automated jailbreaks
Testing revealed 448 jailbreaks for Grok 4.3/4.5 and 249 for Gemini 3.1 Pro, while Claude Opus 4.8, Fable 5, and GPT 5.5/5.6 remained impervious. The cost to successfully jailbreak these models using automated prompt generation was $58 for Grok and $278 for Gemini.
Featured · Adam Gleave
1 source
Daily brief
Get tomorrow's AI brief in your inbox
More stories today
- Pokee-Isaac 28B V0 offers 10M-token context and tool use
- Goodfire Silico helps frontier AI research on vision models
- Codex creates CAD design for lost coffee grinder lid
- Not Diamond launches Code model router for coding agents
- Opus 4.8 quality at half the cost touted for agent infrastructure