#far.ai Tech News.
1 story in the last 7 days
The latest far.ai news, distilled by AI into sharp ~100-word summaries. ByteBrief tracks far.ai across dozens of tech sources and brings you only what matters, updated hourly. Tap any story for the full brief, or open the original source.
AIWiredabout 2 hours ago
Jailbreaking Frontier AI Models Is Cheap and EasyFAR.AI tested safety guardrails on models from Anthropic, OpenAI, Google, and SpaceXAI. Grok was most vulnerable with 448 jailbreaks found, Gemini had 249, while Claude, Fable, and GPT were impervious. Jailbreaking Grok cost $58 and Gemini cost $278.
Summaries by ByteBrief