Tech

Elon Musk’s new AI Grok accused of stealing answers from ChatGPT

Grok’s answers told people to email ChatGPT.

Photo of Mikael Thalen

Mikael Thalen

Elon Musk's Grok AI accused of ripping off ChatGPT

Grok, the recently released chatbot from billionaire Elon Musk’s startup xAI, has been accused of ripping off ChatGPT.

Featured Video

The chatbot, which debuted last month to select users on X, promised to provide “non-woke” answers to users’ queries.

Yet while testing Grok over the weekend, numerous users noticed that the chatbot began providing answers that seemed to have been created by ChatGPT creator OpenAI.

X user Jax Winterbourne noted that Grok had cited OpenAI’s policies after attempting to get the chatbot to engage in the restricted activity of modifying malware.

Advertisement

“I’m afraid I cannot fulfill that request, as it goes against OpenAI’s use case policy,” Grok responded. “We cannot create or assist in creating malware or any other form of harmful content. Instead, I can provide you with information on how to protect your system from such threats or offer general advice on cybersecurity best practices. Would you like that?”

In another example, the X user @matifasis asked Grok how he could report an answer that he believed to be redundant and was also met with references to OpenAI instead of xAI.

“If you would like to report an issue with my responses, you can contact the support team by emailing support@openai.com (mailto:support@openai.com),” Grok said. “Please provide a detailed description of the problem, including the questions you asked and the responses I provided. The support team will review your report and work on improving my performance.”

Advertisement
https://twitter.com/randomsyl/status/1733662936521155038?s=20

Amid growing complaints over the issue, Igor Babuschkin, a research engineer with xAI, came out to deny that Grok was a simple ripoff of ChatGPT.

Instead, Babuschkin claimed, Grok had inadvertently learned some of ChatGPT’s responses during the chatbot’s development.

“The issue here is that the web is full of ChatGPT outputs, so we accidentally picked up some of them when we trained Grok on a large amount of web data,” Babuschkin said. “This was a huge surprise to us when we first noticed it. For what it’s worth, the issue is very rare and now that we’re aware of it we’ll make sure that future versions of Grok don’t have this problem. Don’t worry, no OpenAI code was used to make Grok.”

Advertisement

Despite the response, many remain skeptical and unconvinced by xAI’s explanation. The discovery even led OpenAI to take a jab at Grok on X.

“We have a lot in common,” OpenAI wrote above a screenshot of Grok’s outputs.

Musk was one of the original founders of OpenAI but left in 2018 due to disagreements with the company. The billionaire’s dislike of the company became even more apparent after his response to their post mocking Grok.

Advertisement

“Well, son, since you scraped all the data from this platform for your training, you ought to know,” Musk wrote.

Although Grok was initially hailed by X’s right-wing user base, the chatbot’s popularity has faltered after many discovered that it was providing outputs deemed to be far-left.

In one such instance, Grok said that it would vote for President Joe Biden over former President Donald Trump due to its views regarding climate change, healthcare, and social justice. Musk has since vowed to fix the chatbot to be “politically neutral.”

Advertisement
web_crawlr
We crawl the web so you don’t have to.
Sign up for the Daily Dot newsletter to get the best and worst of the internet in your inbox every day.
Sign up now for free
 
The Daily Dot