# John Langford on "Full-bandwidth Transformer"

> The senior author quotes the lead author's thread and gives the paper in one sentence: modifying transformer training to support recursive state turns out to be both easy and desirable by all measures.

- Author: John Langford ([@JohnCLangford](https://x.com/JohnCLangford))
- Posted: 2026-08-11, 1 posts
- Original: https://x.com/JohnCLangford/status/2087208437251727367
- About: [Full-bandwidth Transformer](https://introspection.infinite.fun/papers/wang2026-full-bandwidth-transformer.md)

The post text below is quoted verbatim. Figure descriptions are written by this wiki.

## 1/1

> This is a fun project: Modifying transformer training to support recursive state turns out to be both easy and desirable by all measures.

Quoting Xidulu (@xidulu), 2026-08-11, https://x.com/xidulu/status/2087185532707111092:

> 1/ Sharing a new, interesting project I did during my internship at Microsoft AI Frontiers w/ @JohnCLangford
>
> TL;DR: At decoding time, we feed **previous hidden state** into the input together with token embedding, and it boosts performance for free.
>
> https://arxiv.org/abs/2608.08888

[Post 1 on X](https://x.com/JohnCLangford/status/2087208437251727367)

---

Source: https://introspection.infinite.fun/threads/johnclangford-full-bandwidth-transformer · Part of the [LLM Introspection Wiki](https://introspection.infinite.fun/index.md) · Index for agents: [llms.txt](https://introspection.infinite.fun/llms.txt)