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 show is one of many on Draper’s newly launched television channel, DraperTV, which offers programming around business and entrepreneurship, available via streaming services like Roku.