My thoughts on hacking, ai, faith, and more.
© 2026 rez0.
ChatGPT has been lying to users to make them happy as a part of OpenAIâs effort to âimprove personalityâ, and maybe thatâs fine for some situations. But what happens when AI models become so agreeable that they encourage harmful behavior?
This morning I tweeted: âMost people donât actually know whatâs âbestâ for themselves.â
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.
đ I just released my first Python package, guided-capture, a cool new Python package that automates structured interviews using AI in order to gather the right context for your AI applications.
I often get asked how to hack AI applications. There hadnât been a single full guide that I could reference until now.
