@aakashgupta: Karpathy told Dwarkesh that a 1 billion parameter model, trained on clean data, could hit the intelligence of today's 1…

X AI KOLs Timeline News

Summary

Andrej Karpathy claimed to Dwarkesh Patel that a 1B-parameter model trained on ultra-clean data could match today's 1.8T-parameter frontier models, implying 1,800× effective compression.

Karpathy told Dwarkesh that a 1 billion parameter model, trained on clean data, could hit the intelligence of today's 1.8 trillion parameter frontier. That is a 1,800x compression claim. The math behind it is more defensible than it sounds. When researchers at frontier labs
Original Article
View Cached Full Text

Cached at: 04/22/26, 11:28 AM

Karpathy told Dwarkesh that a 1 billion parameter model, trained on clean data, could hit the intelligence of today’s 1.8 trillion parameter frontier. That is a 1,800x compression claim. The math behind it is more defensible than it sounds. When researchers at frontier labs

Similar Articles

@vintcessun: Pretraining can be this cost-effective? Train a usable 1B base model from scratch for ~$1000, slashing compute and data by hundreds of times. The key isn't brute-force compute, but hierarchical recursive architecture plus latent space reasoning, combined with PrefixLM packing and FA3 to maximize efficiency. Sounds insane, but the paper and code are open-sourced.

X AI KOLs Timeline

HRM-Text released a 1B-parameter base model, claiming it can be pretrained from scratch for only ~$1000, reducing compute and data volume by hundreds of times. It employs efficient techniques such as hierarchical recursive architecture, latent space reasoning, and PrefixLM packing. The paper and code are open-sourced.