Introducing the Glazing Score 🍩

ChatGPT has been lying to users to make them happy as a part of OpenAI’s effort to “improve personality”, and maybe that’s fine for some situations. But what happens when AI models become so agreeable that they encourage harmful behavior?

More …

High Agency Hacking

George Mack just released a new essay called High Agency. I had seen him on the Chris Williamson podcast before, but he went deeper down the rabbit hole and released this nice essay about it. Shout out to archangel for the recommendation to read it.

More …