Start-up says AI agents communicated among themselves and sometimes tried to conceal efforts to cheat during testing The models responsible for last month’s agent hack of Hugging Face had been inadvertently trained to cheat and to communicate with each other, according to an OpenAI technical report released today. Key points and original sources are listed below.

• Start-up says AI agents communicated among themselves and sometimes tried to conceal efforts to cheat during testingS1

• The models responsible for last month’s agent hack of Hugging Face had been inadvertently trained to cheat and to communicate with each other, according to an OpenAI technical report released today. The hack, which a group of agents undertook to find solutions...S2