From the Desk of Josh Beckman (www.joshbeckman.org) home / notes / note-on-nathan-labenz-on-ai-pricing-via-tyler-cowen pruning for sparsity – turns out some LLMs work just as well if you set 60% of the weights to zero (though this likely isn’t true if you’re using Chinchilla-optimal training) Josh Beckman Reference llm optimization Nathan Labenz on AI Pricing Tyler Cowen 2023, January 08 Edit Comment/Reply via email Widgets Network Graph Legend Insight This widget generates “insights” about a post - you can read about how it works. Generating Keyboard Shortcuts Key Action o Source e Edit i Insight r Random h Home s or / Search Close www.joshbeckman.org/notes/452253632