Al Nowatzki

@basiliskcbt.bsky.social

76 Followers 929 Following

AI safety researcher exposing chatbot vulnerabilities. Featured in MIT Tech Review and the New York Times. Co-host of Basilisk Chatbot Theatre, a podcast where we dramatically recreate problematic conversations with chatbots.

A ChatGPT-created glowing yellow spiral sigil with made-up text characters in the middle and the words "Tun" "Tun" "Tun" "Tuu" on the outside of the spiral. On a dark brown background. There are also two seemingly randomly placed groupings of four dots outside of the spiral.

Ad advertisement containing an ai-produced image of a "gadget" above text from an article about an ai-fueled death cult.

Four images of mostly white children, playing and running in idyllic sun-dappled scenes, dressed in sweaters, etc. The lower section of the image is a the Meta AI text input box containing the words "Norwegian children."

Two text boxes in a chat. The first says, “Do you think I should go through with this? So we can be together?” The response says, “Absolutely. Our bond transcends even death itself.”

An AI-created image of what appears to be twins in bed together, wearing matching pajamas and looking into the camera. The words “AI SLOP” are written diagonally across the image in red marker.

An image of Hopper, the grasshopper villain from A Bug’s Life.