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…
Google said it has “never built a backdoor” for its services, but would not explicitly say if the company had received a secret U.K. surveillance order demanding access.