# H-Net learns to tokenize code variable names and scales better than BPE

> Original title: Super interesting result: H-Net learns to dynamically tokenize variable names in coding data as separate tokens, and it scales much bette...

- Source: Tri Dao
- Published: 2026-10-28T19:49:12.000Z
- Bad Influence: https://badinfluence.news/items/m8e4i6d64bxxotko8z0ffv4i1
- Original: https://x.com/tri_dao/status/2115531348161028374

## Summary

Tri Dao says H-Net dynamically tokenizes variable names in coding data as separate tokens. He reports it scales much better on code than BPE. The post quotes @_albertgu, who says the new H-Net version gains up to 3-5x efficiency in controlled scaling law experiments and matches an 11T-token open-source model with about 10x less data and compute at larger scale.

## Post

Super interesting result: H-Net learns to dynamically tokenize variable names in coding data as separate tokens, and it scales much better on code compared to BPE

## Quoted post @_albertgu

> I've always believed that intelligence should come from simple, general building blocks that learn their own abstractions directly from raw data; in other words, the bitter lesson. I think we're finally seeing a real step towards AI that can learn from all data.
> 
> Language modeling on raw bytes is a microcosm of this ideal, and to me it's a central problem in AI: if we can't build LLMs that learn end-to-end from bytes, how will we handle the rest of the world's data that we understand even less?
> 
> Last year we introduced hierarchical networks (H-Nets) as a first step. Our new version finds up to 3-5x efficiency gains in controlled scaling law experiments, and at larger scale matches an open-source model trained on 11T tokens with ~10x less data and compute. The posts below walk through what we found and why we think it works.

https://x.com/_albertgu/status/2115502110578290900