We want to update you on an incident that happened with our Grok response bot on X yesterday.
What happened:
On May 14 at approximately 3:15 AM PST, an unauthorized modification was made to the Grok response bot's prompt on X. This change, which directed Grok to provide a specific response on a political topic, violated xAI's internal policies and core values. We have conducted a thorough investigation and are implementing measures to enhance Grok's transparency and reliability.
What we’re going to do next:
- Starting now, we are publishing our Grok system prompts openly on GitHub. The public will be able to review them and give feedback to every prompt change that we make to Grok. We hope this can help strengthen your trust in Grok as a truth-seeking AI.
- Our existing code review process for prompt changes was circumvented in this incident. We will put in place additional checks and measures to ensure that xAI employees can't modify the prompt without review.
- We’re putting in place a 24/7 monitoring team to respond to incidents with Grok’s answers that are not caught by automated systems, so we can respond faster if all other measures fail.
I couldn’t stop fucking laughing. I’m wheezing. It’s unhealthy.
They have this thing acting like that for the whole day… and then more than a day later claim it was hacked.
Well it is a LLM, it is going to make up some strange claims when you ask it about why it was trained. We know LLM output cannot be trusted and it gives answers that are often not true but convenient for the people asking the questions. I’m a bit disappointed so many people who should know better now trust the output.
E: I’m sad that this was all on the guiding prompt level and not that they just dumped more white genocide related training data into the model causing it to collapse.
Well it is a LLM, it is going to make up some strange claims when you ask it about why it was trained. We know LLM output cannot be trusted and it gives answers that are often not true but convenient for the people asking the questions. I’m a bit disappointed so many people who should know better now trust the output.
E: I’m sad that this was all on the guiding prompt level and not that they just dumped more white genocide related training data into the model causing it to collapse.
As always, whatever nefarious ends Elon and Co. may have us undercut by their being greedy and incompetent in equal measure.