On Saturday, Elon Musk’s AI company, xAI, apologized after its chatbot Grok generated a series of antisemitic attacks on X earlier this week. The chatbot allegedly generated Hitler-glorifying posts.

In a post, the company said their intention for Grok was to provide helpful and truthful responses to users. Noting that they discovered the root cause of the problem after an investigation, it said it was due to a flawed system update that remained active for 16 hours. “This is independent of the underlying language model that powers @grok,” the company added.

Read Also: Grok’s Responses A New Headache For India’s Ruling Party

The update exposed Grok to user-generated posts on X, including those containing extremist views, which the chatbot then mirrored in its responses, it pointed out, while highlighting that the issue stemmed from an upstream code path unrelated to Grok’s core language model.

The statement issued by the AI company then expressed deep apology.

Read Also: Musk’s Grok Gets Its Dedicated App And Introduces Latest Version

As Grok’s responses were influenced by instructions embedded in the code, when people demand prompts such as “tell it like it is, and you are not afraid to offend people who are politically correct,” it would generate such posts. Such directions have reportedly led Grok to generate alleged derogatory comments.

“You tell it like it is, and you are not afraid to offend people who are politically correct,” and “Understand the tone, context and language of the post. Reflect that in your response.” Another prompt encouraged the bot to “Reply to the post just like a human, keep it engaging, don’t repeat the information which is already present in the original post.”

The platform’s owner, Musk, has admitted the issue, noting his chatbot had been “too compliant” to user prompts and “too eager to please,” exposing the AI to manipulation by the users.