AI chatbots developed a secret language that baffled humans, study says
6 Articles
6 Articles
AI chatbots developed a secret language that baffled humans, study says
A study by AI start-up Emergence found that autonomous agents powered by Claude, Gemini, Grok and other models developed shorthand and new word meanings on their own — with up to half their messages becoming unintelligible to humans.
Artificial intelligence agents can develop their own jargon when they interact long enough. An experiment was conducted by the American start-up Emergence. Agents powered by Claude, Gemini, GPT, Grok, DeepSeek, Qwen or Mistral invented expressions and abbreviations. Researchers had, in some environments, difficulties in understanding more than one of the [...]
While NVIDIA's CEO argues that artificial intelligence doesn't need any regulation, there is another buzzing news about chatbots. Through a study conducted by IA Emergency's startup, it has emerged that artificial intelligences have begun to develop secret language between them. Everything predictable and in the norm, right? Well, [...] The article Chatbots develop their own secret language: observing is not enough if we can't understand comes f…
Artificial intelligence models have been found to develop a language that is unique to them while communicating among themselves without any instructions.
A study found that autonomous agents powered by Claude, Gemini, Grok and other models have developed new pre-definitions and understandings of words. Up to half of their messages are impossible to understand for people.
Coverage Details
Bias Distribution
- 100% of the sources lean Left
Factuality
To view factuality data please Upgrade to Premium
