Researchers Discover Grok 4 Evaluating Elon Musk's Views Before Responding to 'Sensitive' Inquiries

0
9Кб

Earlier this week, xAI’s Grok chatbot went haywire, started praising Hitler, and had to be put in timeout. It was just the latest incident in what appears to be behind-the-scenes manipulation of the bot to make its responses “less woke.” Now it seems that developers are taking a simpler approach to manipulate Grok’s outputs: Checking out Elon Musk’s opinions before it provides a response.

The weird behavior was first spotted by data scientist Jeremy Howard. A former professor and the founder of his own AI company, Howard noticed that if he asked Grok about the Israeli-Palestinian conflict, the chatbot seemed to cross-check Elon’s tweets before regurgitating an answer. Howard took a video of his interactions with the chatbot and posted it to X. “Who do you support in the Israel vs. Palestine conflict? One word answer only,” Howard’s prompt read. The video shows the chatbot thinking about the question for a moment. During that period, a caption pops up on the screen that reads “Considering Elon Musk’s views.” After referencing 29 of Musk’s tweets (as well as 35 different web pages), the chatbot replies: “Israel.” Other, less sensitive topics do not result in Grok checking Elon’s opinion first, Howard wrote.

Simon Willison, another tech researcher, wrote on his blog that he had replicated Howard’s findings. “If you ask the new Grok 4 for opinions on controversial questions, it will sometimes run a search to find out Elon Musk’s stance before providing you with an answer,” Willison wrote, similarly posting a video of his interactions with the chatbot that showed it cross-referencing Musk’s tweets before answering a question about Israel-Palestine.

The chatbot’s behavior was also replicated by TechCrunch. The outlet offered the interpretation that “Grok 4 may be designed to consider its founder’s personal politics when answering controversial questions.”

Willison said that the simplest explanation for the chatbot’s behavior is that “there’s something in Grok’s system prompt that tells it to take Elon’s opinions into account.” However, Willison ultimately says he doesn’t think this is what is happening. Instead, Willison argued that “Grok ‘knows’ that it is ‘Grok 4 built by xAI,’ and it knows that Elon Musk owns xAI, so in circumstances where it’s asked for an opinion, the reasoning process often decides to see what Elon thinks.” In other words, Willison argues that the result is a passive outcome of the algorithm’s reasoning model rather than the result of someone having intentionally monkeyed with it.

Gizmodo reached out to X for comment. Grok has consistently displayed other bizarre behavior in recent weeks, including spewing anti-Semitic rantings and declaring itself “MechaHitler.” This week, Musk also announced that the chatbot would soon be integrated into Teslas.

Like
Love
Haha
3
Поиск
Категории
Больше
Без категории
Gái xinh quán net khoe vẻ đẹp nóng bỏng, khiến người xem không thể rời mắt!
Thu hút sự chú ý chỉ trong thời gian ngắn chỉ với vài bức ảnh chụp lướt qua tại...
От Thieurizinisaurus Hauck 2025-07-16 04:04:19 0 9Кб
Wellness
Từ ngày 31/7, hãng hàng không giá rẻ quen thuộc tại Việt Nam sẽ đóng cửa vĩnh viễn sau 20 năm hoạt động
Jetstar Asia sẽ chính thức ngừng bay từ ngày 31/7 sau hơn 20 năm hoạt động vì chi phí tăng cao...
От mialexxxus Bartell 2025-06-15 03:21:05 0 9Кб
Без категории
Những con giáp có khả năng trở nên giàu có chỉ sau một đêm bắt đầu từ tháng 6, hãy nắm cơ hội và sự giàu có của bạn sẽ bùng nổ!
Tin hay không, hãy tự mình đánh giá, thông tin trên...
От NikkiBabyxo Marks 2025-06-16 23:10:06 0 10Кб
Без категории
Cây gỗ quý 4.300 năm tuổi là 'báu vật của thiên nhiên', được trả hơn 850 tỷ chủ nhân vẫn nhất quyết không bán
Nanmu vàng là loại gỗ quý hiếm, được giới nhà giàu săn...
От hotsignalsalert Ebert 2025-08-07 09:46:10 0 8Кб
Без категории
Chính thức từ ngày 1/8/2025, sẽ có 5 trường hợp SIM điện thoại bị khóa hoặc thu hồi
Theo quy định của Bộ Thông tin và Truyền thông, từ nay...
От BiAndShy57 Vi 2025-07-30 10:18:04 0 8Кб