Stephanie Palazzolo(@steph_palazzolo):OpenAI’s Astra AI uses a new reasoning approach called “recurrent depth.” Though it can help model costs and performance, researchers are concerned bc it obscures a model’s thinking process, making it more difficult to monitor. w/ @amir @rocketalignment

Stephanie Palazzolo

@steph_palazzolo

Writing AI Agenda @theinformation, texan, & horror movie aficionado // reach me at stephanie@theinformation.com or on Signal at 979-599-8091

가입 October 2015

5K 팔로잉 중 23.3K 팬

Stephanie Palazzolo@steph_palazzolo

2026.09.02 01:04

OpenAI’s Astra AI uses a new reasoning approach called “recurrent depth.” Though it can help model costs and performance, researchers are concerned bc it obscures a model’s thinking process, making it more difficult to monitor. w/ @amir @rocketalignment