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…
Now, when users search for places in Map like restaurants, hotels, or concert venues, they’ll see a new “know before you go” tips section that will surface important information about the place.