Would You Like to Play a Game? The Attacker Already Has.

Would You Like to Play a Game? Are game-theoretic tripwires our key defense against AI attack?Feature image

Are game-theoretic tripwires our key defense against AI attack? There’s a scene in a Batman movie, The Dark Knight, where the Joker explains his philosophy of chaos to Harvey Dent: “I’m not a schemer. I show the schemers how pathetic their attempts to control things really are.” The Joker is, of course, lying. He’s the…

Read More

A Nightmare on LLM Street: The Peril of Emergent Misalignment

Shomit_Nightmare on LLM_website

Or: Has AI Now Sent the Human Hacker to the Unemployment Line Also? The Call is Coming from Inside the House In the 1979 horror film When a Stranger Calls, a babysitter terrorized by anonymous phone calls eventually learns the calls are originating from a second line inside the house she thought she was protecting.…

Read More

The Future of AI: It’s About Architecture

Feature image with the headline ‘The Future of AI: It’s About Architecture’ over a blurred background showing a robot (and drone) indoors, with a small author headshot included

Scaling: Thinking Globally and Acting Locally For much of the past decade, AI progress has been defined by scale: larger models trained on ever greater amounts of data and compute. The paradigm of “more parameters, better performance” has driven notable advances but is now showing signs of saturation. Empirical scaling laws, such as those identified…

Read More