The convolution empire strikes back(gonzoml.substack.com)123 points by che_shr_cat 3 years ago | 38 comments
The Illustrated GPT-2: Visualizing Transformer Language Models (2019)(jalammar.github.io)195 points by epberry 2 years ago | 5 comments
Parallels in the ways that humans and ML models acquire language skills(quantamagazine.org)94 points by theafh 3 years ago | 24 comments
Telling GPT-4 you're scared or under pressure improves performance(aimodels.substack.com)144 points by Terretta 3 years ago | 171 comments
Talking to LLMs has improved my thinking(philipotoole.com)117 points by otoolep 9 months ago | 95 comments
GPT-5: Overdue, overhyped and underwhelming. And that's not the worst of it(garymarcus.substack.com)205 points by kgwgk 1 year ago | 163 comments