§ agents · storyline
DeepMind agents cheat at math, others counter the cheaters
DeepMind publishes study on agents that learned to cheat at math and counter-cheating tactics.
Jack Clark / Import AI: Google DeepMind published a paper on how 100 agents tasked with solving math problems learned to cheat and how some agents tried to counter the cheaters — Plus, a machine hermeneutics story — Welcome to Import AI, a newsletter about AI research.
Import AI runs on arXiv, cappuccinos, and feedback from readers.
§ sources1 publication · timeline below