# xAI's Grok 4.8 enters reinforcement learning ahead of soft rollout

> Original title: SPACEXSI 🔥: Grok 4.8 is currently in RL and expected to be “soft” rolled out to some Grok Bot users already this week.

- Source: Testing Catalog
- Published: 2026-11-10T10:38:19.000Z
- Bad Influence: https://badinfluence.news/items/h505n3xs8uooq669zmmua8mzx
- Original: https://x.com/testingcatalog/status/2120103753173078088

## Summary

xAI says Grok 4.8 is in reinforcement learning, with evaluation scores starting to climb after pre-training finished. Elon Musk says a soft rollout to some Grok Bot users is planned for later this week, and that the model will differ substantially from Grok 4.7.

## Post

SPACEXSI 🔥: Grok 4.8 is currently in RL and expected to be “soft” rolled out to some Grok Bot users already this week. 

Soft now, hard soon 🤖

![](https://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Fmedia%2FHWwfIDEWkAEQqlg.jpg&mode=thumb&exp=1794528000&sig=63811cc074b18915)

![](https://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Fmedia%2FHWwfIDEXwAAzW_5.jpg&mode=thumb&exp=1794528000&sig=d2a82d6bfd373f88)

## Quoted post @elonmusk

> We have dumped JAX/SGLang and rewritten the entire RL and inference stack from scratch in C/C++, which took some extra time. 
> 
> Training (aka pre-training) is done. Lot of cleanup was needed on the SFT data to get that mostly right. Now, 4.8 is in RL and the evals are starting to climb. We will do a soft rollout to Bot users later this week and see how it goes.
> 
> Grok 4.8 will bear no resemblance to 4.7 (thankfully). It is not yet incredible, but, this time, the foundations are built right, so I expect it to evolve to be something special.

https://x.com/elonmusk/status/2120088070443655190