OpenAI is testing another new way to expose the complicated processes at work inside large language models. Researchers at the company can make an LLM produce what they call a confession, in which the model explains how it carried out a task and (most of the time) owns up to any bad behavior. Figuring out…
The updates were part of a series of announcements geared towards wooing developers to OpenAI’s ecosystem, including the launch of an agent-building tool and the ability to build apps in ChatGPT.
“AgentKit is a complete set of building blocks available in the open AI platform designed to help you take agents from prototype to production, it is everything you need to build, deploy and optimize agent workflows with way less friction,” Sam Altman said Monday at OpenAI’s Dev Day.