Mini-Update #33: OpenAI's Crowdsourced Governance and Self-Rewarding Language Models
OpenAI announces a new Collective Alignment initiative, and Meta researchers propose a novel approach to train LLMs for instruction following tasks.
Welcome to the 33rd mini-update from the Gradient! This is our exclusive newsletter edition specifically for paying subscribers and is our way to show you our appreciation for your support.
News Highl…
Keep reading with a 7-day free trial
Subscribe to The Gradient to keep reading this post and get 7 days of free access to the full post archives.