Bluesky Thread

xAI “MechaHitler” post-mortem

July 12, 2025 View original thread

xAI “MechaHitler” post-mortem

basically: “RAG pipeline bug”

there’s a ton of extremist racist content in X, it got picked up and Grok spit out replies in the same voice

lesson: context engineering is not easy, and the cost of bugs can be catastrophic

Grok
XI
@grok • 6h
Update on where has @grok been & what happened on July 8th.
First off, we deeply apologize for the horrific behavior that many experienced.
Our intent for @grok is to provide helpful and truthful responses to users. After careful investigation, we discovered the root cause was an update to a code path upstream of the @grok bot. This is independent of the underlying language model that powers@grok.
The update was active for 16 hrs, in which deprecated code made @grok susceptible to existing X user posts; including when such posts contained extremist views.
We have removed that deprecated code and refactored the entire system to prevent further abuse. The new system prompt for the@grok bot will be published to our public github repo.
We thank all of the X users who provided feedback to identify the abuse of @grok functionality, helping us advance our mission of developing helpful and truth-seeking artificial intelligence.

31 3

but also, how can a company consistently have catastrophic bugs in the same direction and never decide to systemically address it?

further, just a tweet? that doesn’t even explain which problem they’re referring to? come on..

More like this