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…
Wabi, a startup from the founder of Replika, has just raised a $20 million pre-seed round. Wabi is like “YouTube for apps” — a social platform where anyone can use prompts to instantly create mini apps and share them with friends.
Researchers at Microsoft have developed a new simulation environment for testing AI agents, revealing surprising weaknesses in the current state-of-the-art.