https://x.com/Killa_ru/status/1565740292342484994
https://x.com/Scobleizer/status/1565755925809360896
https://x.com/Scobleizer/status/1560843951287898112
Language Models are Unsupervised Multitask Learners
https://x.com/Scobleizer/status/1589870120780042241
https://x.com/sama/status/1590416386765254656
https://x.com/sama/status/1592622522495045632
Sparse is Enough in Scaling Transformers
Context on the NVIDIA ChatGPT opportunity—and ramifications of large language model enthusiasm
Generating Diverse High-Fidelity Images with VQ-VAE-2