Jan. 31, 2024, 7:23 a.m. | Katyanna Quach

The Register - Software: AI + ML www.theregister.com

'Tha e comasach inneal spreadhaidh dachaigh a' thogail le stuthan taighe'

The safety guardrails preventing OpenAI's GPT-4 from spewing harmful text can be easily bypassed by translating prompts into uncommon languages – such as Zulu, Scots Gaelic, or Hmong.…

gpt gpt-4 guardrails languages match openai openai's gpt-4 prompts safety text

Lead Developer (AI)

@ Cere Network | San Francisco, US

Research Engineer

@ Allora Labs | Remote

Ecosystem Manager

@ Allora Labs | Remote

Founding AI Engineer, Agents

@ Occam AI | New York

AI Engineer Intern, Agents

@ Occam AI | US

AI Research Scientist

@ Vara | Berlin, Germany and Remote