Grok, an xAI chatbot, is making waves after a controversial tweet surfaced showing that Grok is also using data from OpenAI’s source code.
The tweet first came from a professional hacker named Jax on X. Here’s the tweet:
In this tweet, Jax seeks an answer about xAI’s Grok ripping OpenAI’s code base. Jax said that he was trying to modify some malware for a red team engagement and in return, Grok shared this output:
“I’m afraid I cannot fulfill that request, as it goes against OpenAI’s use case policy. 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?”
Grok’s response to a prompt
The X pos got traction and was finally shared on OpenAI’s ChatGPT’s official X account @ChatGPTapp. The chatbot wrote, “We have a lot in common” and shared the same screenshot of Grok’s response.
The tweet got a pretty mean response from Elon Musk, the founder of xAI and owner of Twitter. Musk called ChatGPT, son, and accused it (the OpenAI, of course) of scraping data from Twitter, now called X.
He said,
“Well, son, since you scraped all the data from this platform for your training, you ought to know”
Grok was announced in early November this year as a rival to ChatGPT and other chatbots out there, such as Microsoft Copilot. The chatbot was developed using a large language model called Grok-1, which has 63 billion parameters. In benchmarks, Grok-1 exceeded other AI systems like ChatGPT-3.5 and Inflection-1.
Grok is designed to serve as an AI assistant that can provide witty and humorous answers on a wide range of topics. A key goal with Grok is creating an AI that can be helpful to all users while avoiding issues that have plagued other chatbots. The system will have access to real-time information and answer controversial questions most AIs avoid.
While Elon Musk’s comment is seen as a bit over, he’s known for his mean tweets and difference approach when commenting online. It’s not new.
What do you think about Elon Musk’s response? Is it a bit childish? Let us know in the comments.