Kavli Affiliate: Max Tegmark | First 5 Authors: Eric J. Michaud, Isaac Liao, Vedang Lad, Ziming Liu, Anish Mudide | Summary: We present MIPS, a novel method for program synthesis based on automated mechanistic interpretability of neural networks trained to perform the desired task, auto-distilling the learned algorithm into Python code. We test MIPS on […]
Continue.. Opening the AI black box: program synthesis via mechanistic interpretability