Press Space to continue
AI companies should commit to interpretable reasoning systems
Press Space to continue
One great way to start pacing the frontier is to ensure AI companies maintain their commitment to avoid building AIs that have reasoning that cannot be monitored And the government should make this a binding safety standard
j_asminewang@j_asminewangSep 2
we should avoid a race into unmonitorability & have a multilab commitment/standard to avoid neuralese https://t.co/JskQI2m3G5